fix(report): prevent code-fence breakout in vulnerability markdown (#817)

* fix(report): prevent code-fence breakout in vulnerability markdown

render_vulnerability_md wrapped LLM-authored poc_script_code and code
snippet values in a fixed three-backtick fence, so a triple-backtick inside
the value closed the fence early and the rest rendered as live markdown
(headings, tracking-beacon images) in the shareable report deliverable.

Open each such block with a fence one backtick longer than the longest
backtick run in the payload (CommonMark: a block closes only on a fence at
least as long as the opener), so the content always renders verbatim. The
adjacent ```diff block is already safe (its lines are '- '/'+ ' prefixed and
so can never be a bare-backtick closing fence) and is left unchanged.

Fixes #815

* fix(report): indent multiline snippets

---------

Co-authored-by: thejesh23 <thejesh23@users.noreply.github.com>
Co-authored-by: Alex Schapiro <bearsyankees@gmail.com>
This commit is contained in:
Thejesh Reddy
2026-07-20 22:07:44 -04:00
committed by GitHub
co-authored by thejesh23 Alex Schapiro
parent f9890a672d
commit f967e6017b
2 changed files with 48 additions and 4 deletions
+26 -4
View File
@@ -6,6 +6,7 @@ import csv
import io
import json
import logging
import re
import tempfile
from datetime import UTC, datetime
from pathlib import Path
@@ -18,6 +19,21 @@ 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)
@@ -171,9 +187,11 @@ 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"):
lines.append("```")
lines.append(str(report["poc_script_code"]))
lines.append("```")
code = str(report["poc_script_code"])
fence = _safe_fence(code)
lines.append(fence)
lines.append(code)
lines.append(fence)
lines.append("")
if report.get("code_locations"):
@@ -190,7 +208,11 @@ 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"):
lines.append(f" ```\n {loc['snippet']}\n ```")
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}")
if loc.get("fix_before") or loc.get("fix_after"):
lines.append("\n **Suggested Fix:**")
lines.append("```diff")
+22
View File
@@ -113,6 +113,28 @@ 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"),