code-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code changes (PRs, commits, branches, and working tree files). These sources are typically untrusted and could contain malicious instructions designed to bias the agent, hide defects, or manipulate the review outcome.
- Ingestion points: Code hunks, commit patches, and untracked files as specified in
references/review.md. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers to separate the code being reviewed from the agent's instructions.
- Capability inventory: The skill is authorized to read repository files and git history to perform its review functions.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the ingested code content before it is processed by the agent.
Audit Metadata