recall
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a read-only search capability for internal memory. Analysis of the instructions and examples shows no evidence of prompt injection, data exfiltration, or malicious commands. The instructions explicitly include anti-patterns that forbid the AI from fabricating data (hallucination prevention), which is a positive safety control. External references are limited to local troubleshooting files and related internal tool documentation.
Audit Metadata