co-ceo
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and organizational frameworks. There are no scripts (.sh, .py, .js) or binary files included.
- [SAFE]: The instructions establish a professional persona (CEO/Founder) without attempting to bypass AI safety guardrails or override system instructions.
- [SAFE]: No data exfiltration or credential access patterns were detected. The skill does not request tools or permissions for network or file system operations.
- [SAFE]: The skill includes proactive security prompts for the user, such as 'Are secrets handled properly?' and 'What is the attack surface?' when reviewing technical architectures.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user plans and strategies. However, because the skill has no access to sensitive tools, file-writing capabilities, or network operations, the risk of an injection attack leading to system compromise is non-existent. There are no dangerous capabilities to exploit.
Audit Metadata