post-implementation-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources that could contain untrusted content, such as GitHub Issues, Pull Requests, and design documents.
- Ingestion points: Instructions in the Audit section (steps 1, 3, and 5) involve reading repository instructions, design documents, GitHub Issues, and Pull Requests.
- Boundary markers: The instructions do not define specific delimiters or instructions to the agent to ignore embedded commands within the audited data.
- Capability inventory: The skill allows the agent to run repository verification commands (step 9) and read files, although it explicitly restricts modifications (e.g., no editing code or pushing commits).
- Sanitization: There is no mention of sanitizing or filtering content retrieved from the external sources before processing.
Audit Metadata