update-pr-review

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes human comments from external GitHub PRs to update internal guidance, creating a surface for indirect prompt injection.
  • Ingestion points: scripts/aggregate_review_feedback.py uses the gh CLI to fetch human_review_comments, conversation_comments, and PR review bodies.
  • Boundary markers: The instructions do not specify structured delimiters for the ingested JSON feedback, relying on the agent's internal parsing.
  • Capability inventory: The skill can suggest changes to repo-local review skills (e.g., .github/skills/review-pr-repo/SKILL.md), which are subsequently applied by scripts/apply_guidance_output.py and validated by scripts/validate_write_surface.py using git commands.
  • Sanitization: SKILL.md provides natural language guardrails, instructing the agent to abstract patterns rather than copying raw text, keep wording concise, and avoid pasting raw JSON into skill files.
  • [COMMAND_EXECUTION]: The skill relies on local shell command execution for its data gathering and validation workflows.
  • scripts/aggregate_review_feedback.py: Executes gh api graphql, gh repo view, and gh pr list to retrieve repository data and PR feedback.
  • scripts/validate_write_surface.py: Executes git diff and git ls-files to ensure no unauthorized files were modified during the process.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 01:12 AM