letta
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious patterns detected. The skill primarily serves as a documentation reference for developers working with the Letta framework.
- CREDENTIALS_UNSAFE (SAFE): Code examples use standard placeholders for API tokens (
<token>,YOUR_TOKEN) rather than hardcoded secrets. - EXTERNAL_DOWNLOADS (SAFE): The skill suggests installing
letta-evalsvia pip, which is the legitimate package associated with the framework's evaluation tools.
Audit Metadata