tao-list-capabilities
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute specific Python helper scripts (e.g.,
list_tao_capabilities.py,list_tao_models.py) to retrieve metadata from local manifest files. These operations are restricted to the local filesystem and vendor-defined paths. - [SAFE]: No prompt injection, data exfiltration, or obfuscation patterns were detected. The skill's behavior is consistent with its role as a metadata discovery tool for the TAO Toolkit.
Audit Metadata