review
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data including pull request descriptions, diffs, comments, and code files, which can contain embedded instructions aimed at influencing the agent's behavior.
- Ingestion points: The skill reads the live PR description, diff, reviews, CI results, and the codebase itself as described in
SKILL.md(steps 1 and 2). - Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the PR data.
- Capability inventory: The agent is instructed to execute shell commands such as
make validate,make check, and local scripts likepython3 .github/scripts/check_skill_routes.py(step 3). - Sanitization: The skill does not define any sanitization or validation steps for the content ingested from the PR before it is processed by the agent.
Audit Metadata