testing
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or safety bypasses were found within the skill's content or logic.\n- [PROMPT_INJECTION]: The skill includes a high-priority instruction using the 'CRITICAL' marker to direct the agent to specific documentation. This is a functional requirement for providing accurate context and does not attempt to override the AI's safety guidelines.\n- [DATA_EXFILTRATION]: The skill references an absolute file path belonging to the author's local project directory (/home/mwguerra/...). This reference is a vendor-owned resource intended for documentation lookup and does not involve the exposure or exfiltration of sensitive user data or credentials.
Audit Metadata