investigate-issue
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized data access patterns were detected. The skill primarily consists of natural language instructions for issue investigation.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it requires the agent to read and process content from GitHub issue bodies. This is a common characteristic of issue-handling skills and is managed by standard agent safety protocols.\n
- Ingestion points: GitHub issue body (referenced in SKILL.md process steps).\n
- Boundary markers: None defined to isolate the issue body content from instructions.\n
- Capability inventory: File reading, code search (grep), git history analysis (blame), and commenting/labeling.\n
- Sanitization: Not specified in the instructions.
Audit Metadata