council
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed exclusively of instructions within the SKILL.md file. It does not include any Python, Node.js, or shell scripts, eliminating risks associated with malicious code execution.
- [SAFE]: The skill leverages the agent's existing capabilities (Read, Write, AskUserQuestion) to facilitate a reasoning process. Analysis found no evidence of credential harvesting, data exfiltration, or unauthorized persistence mechanisms.
- [PROMPT_INJECTION]: The skill utilizes persona-based prompting to simulate a 'council' of advisers. These instructions are designed to improve decision-making quality and do not attempt to override system safety guidelines or extract sensitive environmental data.
Audit Metadata