reality-audit
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of procedural markdown instructions for an agent to perform verification tasks. It does not contain executable scripts, external network requests, or credential-harvesting patterns.
- [SAFE]: The instructions encourage secure software engineering practices, such as verifying code against canonical artifacts rather than scratch builds and checking command exit statuses to ensure test integrity.
- [SAFE]: Trigger words include Russian translations ("проверка реальностью") which are contextually appropriate for the skill's purpose and do not represent malicious homoglyph obfuscation.
Audit Metadata