audit-context
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on reading and analyzing local project files such as
nao_config.yaml,RULES.md, and directory structures to provide health assessments. - [SAFE]: No network operations (exfiltration) or remote code downloads were detected. The skill's behavior is limited to diagnostic text output.
- [SAFE]: The instructions contain explicit guardrails prohibiting the skill from making direct changes ("Diagnose only — never fix"), ensuring human-in-the-loop review for all recommendations.
- [SAFE]: Analysis of the logic shows no evidence of prompt injection, obfuscation, or persistence mechanisms.
Audit Metadata