architect
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is configured as a read-only advisor. The instructions explicitly prohibit the agent from writing files, generating command itineraries, or creating external artifacts. This significantly limits the potential impact of any instructions processed by the skill. The requirement to load skills only from verified locations and adhere to host safety constraints further reinforces a secure posture. No evidence of malicious code, obfuscation, or data exfiltration was found.
Audit Metadata