agent-experience
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to improve the security and reliability of agent-consumed surfaces and contains no malicious code, obfuscation, or dangerous execution patterns.
- [PROMPT_INJECTION]: The skill instructions proactively address risks by defining the trust boundary as an injection surface and providing heuristics for scanning and pinning untrusted tool metadata.
- [DATA_EXFILTRATION]: The instructions include comprehensive guidance on avoiding data exfiltration and protecting PII (Personally Identifiable Information) when designing agent telemetry and tools.
Audit Metadata