agile-refinement
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define clear, benign workflows for document validation and code review. It acts as a passive analyzer and reporter.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (planning files and source code) which presents a surface for indirect prompt injection. This is a low-risk surface as the skill lacks network or file-write capabilities.
- Ingestion points: Project files in the
planning/directory and source code changes identified via$ARGUMENTS. - Boundary markers: No specific boundary markers or 'ignore' instructions are defined for the ingested content.
- Capability inventory: The skill reads local files for analysis; no subprocess calls, file-write operations, or network access are specified in the instructions.
- Sanitization: No explicit sanitization of the content of the files being reviewed is mentioned.
Audit Metadata