discover
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses local imports from the
srcdirectory and standard library modules (pathlib) to perform data processing and ranking tasks. There is no evidence of external package installation or remote script execution. - [SAFE]: Network activity is restricted to a local repository service (
localhost:6363), which does not pose an exfiltration risk under the observed usage. - [SAFE]: No prompt injection, obfuscation, or persistence mechanisms were detected in the skill instructions or code snippets. The interaction with the file system is scoped to a specific local directory (
.agent-memory).
Audit Metadata