review
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that may contain malicious instructions designed to influence the agent's behavior during the review process.
- Ingestion points: Content is pulled from
gh pr view,gh issue view, and files within the codebase (e.g.,CLAUDE.md). - Boundary markers: The instructions lack explicit delimiters or specific prompts to ignore instructions embedded within the reviewed data.
- Capability inventory: The skill uses the
ghCLI and local linting tools to assess code and report findings. - Sanitization: There is no mention of sanitization or filtering for the external data before it is processed by the agent.
Audit Metadata