tao-list-capabilities

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (e.g., list_tao_capabilities.py, list_tao_models.py, and list_tao_platforms.py) via the Bash tool to gather information about TAO application workflows, models, and platforms. This is the primary intended function of the skill and relies on the user's local installation.
  • [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The skill's behavior is consistent with its stated purpose of aiding NVIDIA TAO workflow discovery, and the referenced resources are vendor-specific.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 05:48 PM
Security Audit — agent-trust-hub — tao-list-capabilities