review-me
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core functionality of processing untrusted external data.
- Ingestion points: Untrusted data enters the agent context through
git diffoutputs, PR content, feature branches, and the full scanning of existing repositories in "adopt mode" (SKILL.md). - Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate the untrusted code content, and there are no instructions for the agent to ignore potentially malicious directions embedded within the code being reviewed.
- Capability inventory: The agent has the capability to read files, execute local
gitcommands, and modify the filesystem when applying rule-conformance fixes (SKILL.md). - Sanitization: No sanitization or escaping of the external code content is described before it is interpolated into the agent's context.
Audit Metadata