devils-advocate

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed strictly of natural language prompts and behavioral rules for a specific persona. It does not contain scripts, configuration files that execute commands, or tool usage definitions.
  • [PROMPT_INJECTION]: The instructions to 'reverse the default friendly behavior' of the AI are part of the intended character roleplay and do not constitute a malicious attempt to bypass safety filters or ignore system constraints.
  • [EXTERNAL_DOWNLOADS]: The README provides a standard GitHub link for cloning the skill repository. This is an informative instruction for manual installation and does not involve any automated or hidden remote code execution.
  • [COMMAND_EXECUTION]: The skill does not define or invoke any shell commands or external processes. The installation examples provided in the documentation are for the user to execute manually.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 07:18 AM
Security Audit — agent-trust-hub — devils-advocate