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
Risk Level
SAFE
Analyzed
Jun 23, 2026, 12:04 PM
Security Audit — agent-trust-hub — tao-list-capabilities