fool

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists exclusively of instructional text for a devil's advocate persona. It does not contain any executable code, scripts, or external dependencies.
  • [NO_CODE]: No code or external packages (Python or Node.js) are referenced or used by this skill.
  • [PROMPT_INJECTION]: While the skill contains persona-driven instructions to 'stay in character' and 'speak truth to the king,' these are standard creative prompting techniques for decision-support tools and do not involve bypassing safety guardrails or system instructions.
  • [DATA_EXFILTRATION]: No network activity, hardcoded secrets, or sensitive file path references were found in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:20 PM
Security Audit — agent-trust-hub — fool