docs-review
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (HIGH): The skill lacks sufficient safeguards when processing untrusted external data.
- Ingestion points: The skill uses
mcp__github__get_pull_request_diffandReadtools to ingest documentation content from GitHub PRs and local files (SKILL.md, Step 2 in Review Process). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the ingested documentation as untrusted data or to ignore embedded instructions within that data.
- Capability inventory: The skill possesses significant write capabilities via
mcp__github__add_pull_request_review_comment_to_pending_reviewandmcp__github__submit_pending_pull_request_review(SKILL.md, PR review mode format). - Sanitization: There is no mention of sanitizing or escaping the content read from the diffs before it is used to generate review comments.
Recommendations
- AI detected serious security threats
Audit Metadata