ajiang-review
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as code diffs, repository changes, and user requirements. This creates a surface where instructions hidden within the code being reviewed could attempt to influence the agent's behavior.
- Ingestion points: PR diffs, branch differences, and workspace code files as described in the review process.
- Boundary markers: The instructions do not specify explicit delimiters or warnings for the agent to ignore instructions embedded within the code under review.
- Capability inventory: The agent is instructed to read files, delegate tasks to other agents, and perform verification experiments.
- Sanitization: No sanitization or filtering of the code content is mentioned.
- [NO_CODE]: The skill consists of markdown instructions and templates for record-keeping and does not include any executable scripts, binaries, or automated installation commands.
Audit Metadata