the-consigliere
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and role-play definitions. It does not include any scripts, executable code, or platform-level configuration that could impact system security.
- [PROMPT_INJECTION]: The skill uses persona-enforcement language, such as claiming 'standing authority' and 'outside the chain of command.' These instructions are designed to maintain the agent's analytical objectivity within its thematic framework and do not attempt to bypass system safety guidelines or override developer-level constraints.
- [DATA_EXPOSURE]: While the skill provides instructions for the agent to perform 'Security Audits' (including checking for secret exposure), it does not contain any logic to access, harvest, or transmit sensitive files or credentials from the host environment.
- [COMMAND_EXECUTION]: The skill explicitly states that it 'does NOT write code' and 'does NOT execute tasks,' focusing solely on reviewing and providing architectural advice.
Audit Metadata