principle-prove-it-works
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of text-based guidelines instructing the agent to verify task completion by checking actual artifacts rather than relying on self-reports or indirect evidence.
- [NO_CODE]: There are no scripts, binaries, or automated commands included in the skill. It is a purely documentation-based principle for behavioral guidance.
- [SAFE]: The metadata and instructions do not contain any prompt injection, obfuscation, or data exfiltration patterns.
Audit Metadata