devil-advocate
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill is composed entirely of natural language instructions and structural templates for the agent to follow when acting as a 'Devil's Advocate'.
- [NO_CODE] (SAFE): No scripts, binaries, or shell commands are included or referenced for execution.
- [DATA_EXPOSURE] (SAFE): There are no patterns suggesting access to sensitive files, environment variables, or hardcoded credentials.
- [PROMPT_INJECTION] (SAFE): While the skill uses strong instructional language (e.g., 'NEVER', 'CRITICAL'), these are used legitimately to define the agent's analytical persona and do not attempt to bypass safety filters or extract system prompts.
Audit Metadata