war-council
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill logic consists entirely of prompt instructions for role-playing personas. No malicious code execution, network access, or sensitive data handling was detected.
- [PROMPT_INJECTION]: While the skill utilizes distinct personas (e.g., 'The Ruthless CFO'), these instructions are designed for structured reasoning and do not include patterns to override AI safety constraints or bypass system instructions.
- [DATA_EXFILTRATION]: No network operations or commands to access sensitive configuration files (~/.ssh, ~/.aws, etc.) were found.
- [REMOTE_CODE_EXECUTION]: The skill does not reference external dependencies or download remote scripts for execution.
Audit Metadata