principle-experience-first
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or external dependencies. It is purely composed of instructional prose for design principles.
- [SAFE]: No data ingestion or processing surfaces were found, eliminating the risk of indirect prompt injection.
- [SAFE]: The configuration in
agents/openai.yamlspecifies a restrictive policy (allow_implicit_invocation: false), which is a security-positive setting that prevents the agent from being invoked without explicit user intent.
Audit Metadata