memory
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's behavior is consistent with its intended use for analyzing conversation state and contains no malicious instructions or bypass attempts.
- [EXTERNAL_DOWNLOADS]: Uses the
ejentum-mcpserver, which is an expected external dependency from the author for theharness_memorytool functionality. - [CREDENTIALS_UNSAFE]: The skill utilizes the
EJENTUM_API_KEYenvironment variable for authentication, following standard security practices for secret management.
Audit Metadata