tao-train-deformable-detr

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill instructions and configuration schemas are consistent with its stated purpose of managing NVIDIA TAO object detection workflows.
  • [EXTERNAL_DOWNLOADS]: The skill references container images from NVIDIA's official container registry (nvcr.io). These are well-known and trusted resources required for the skill's operation and do not represent a security risk.
  • [DATA_EXPOSURE]: No hardcoded credentials or sensitive file path access was identified. The skill correctly uses placeholders for user-specified data directories.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data paths. While this represents a potential surface for indirect injection if those sources are malicious, it is a primary function of the skill and the data is processed within the scoped environment of the TAO container.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:35 PM
Security Audit — agent-trust-hub — tao-train-deformable-detr