Debug Helper
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): No malicious patterns, data exfiltration, or prompt injection attempts were detected in the skill instructions. The content focus is on standard software debugging methodologies (Wolf Fence, MRE, dbg macros).
- Indirect Prompt Injection (LOW): The skill is designed to process untrusted external data (runtime panics, user code, and logic errors). While this creates an attack surface, the instructions are purely procedural for agent reasoning and do not include dangerous tool executions or exfiltration paths within the skill definition itself.
Audit Metadata