skill-creator-proposals
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script to perform CRUD operations on files located in
~/.opensquilla/proposals/. This involves listing directories, reading file contents, and moving directories to the~/.opensquilla/skills/path. - [DATA_EXFILTRATION]: While the script reads data from the local filesystem, all operations are restricted to the OpenSquilla environment's state directory. No network requests or data transfers to external domains were identified.
- [SAFE]: The skill is configured as non-user-invocable and disables model invocation, limiting its use to internal automated workflows. Its behavior is consistent with the provided description and vendor context.
Audit Metadata