tao-convert-dataset-format

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected in the skill's instructions or metadata.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the nvidia-tao-daft package via pip. This is a legitimate dependency required for the skill's functionality and originates from a well-known technology provider.
  • [COMMAND_EXECUTION]: The skill provides instructions for executing shell commands using the tao-daft CLI tool. These commands are directly related to the skill's stated purpose of dataset conversion and do not involve unauthorized privilege escalation or destructive operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:10 PM
Security Audit — agent-trust-hub — tao-convert-dataset-format