triage
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains purely instructional logic for an agent to process and route work requests. It does not implement any code execution, network operations, or credential handling.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input in the form of 'requests written in plain words'.
- Ingestion points: User-supplied plain text requests are processed in Step 1 of the SKILL.md.
- Boundary markers: None explicitly defined in the text.
- Capability inventory: The skill instructs the agent to read project files (masterplan, changelog), update issues, and invoke other local skills like
repairorfit-check. - Sanitization: Not applicable as the skill relies on internal classification logic rather than execution of the input content.
Audit Metadata