software-guidelines
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external repository content, which may contain untrusted data.
- Ingestion points: The skill requires the agent to read 'applicable instructions', 'worktree status', and 'affected implementation' (SKILL.md).
- Boundary markers: The instructions do not specify any boundary markers or delimiters for external content.
- Capability inventory: The skill involves implementation of code changes and verification via tests.
- Sanitization: No explicit sanitization or input validation for repository content is mentioned.
Audit Metadata