council
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a prompt-based workflow designed to help users evaluate complex decisions through multiple perspectives. It orchestrates subagents to provide feedback but does not perform any risky technical operations.
- [DATA_EXFILTRATION]: No network communication or data exfiltration patterns were detected. The skill operates entirely within the agent's context and orchestration of subagents.
- [COMMAND_EXECUTION]: The skill does not contain any shell commands or binary execution logic. It explicitly instructs the agent to avoid writing ad-hoc notes to local file paths like
~/.claude/notes. - [REMOTE_CODE_EXECUTION]: No remote code execution patterns, package installations, or external script downloads were found in the instructions.
- [PROMPT_INJECTION]: The instructions do not contain any patterns attempting to override safety guidelines or bypass system constraints. The prompt templates provided for subagents are standard role-playing instructions for specialized personas.
Audit Metadata