repo-issue-triage
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill defines a logical state machine and workflow for managing repository backlogs.
- [NO_CODE]: The skill consists entirely of instructional markdown and metadata without executable scripts or binary files.
- [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data from issues and comments, creating a potential surface for indirect injection. However, since the skill does not grant the agent capabilities to perform network operations, file writes, or command execution, the risk is negligible.
- Ingestion points: External issues, requests, and comments processed in
SKILL.md. - Boundary markers: Absent.
- Capability inventory: Limited to reading code and documentation for analysis.
- Sanitization: None described.
Audit Metadata