tao-train-nvpanoptix3d

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the TAO Toolkit via a specific Python module entrypoint: 'python -m nvidia_tao_pytorch.cv.nvpanoptix3d.entrypoint.nvpanoptix3d'. This is the standard method for executing training, evaluation, and inference tasks within the toolkit image.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it ingests untrusted data from external dataset files.
  • Ingestion points: The agent reads metadata from JSON files specified by 'dataset.train.json_path', 'dataset.val.json_path', and 'dataset.test.json_path' in 'references/skill_info.yaml'.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions that might be embedded within these metadata files.
  • Capability inventory: The skill has the capability to execute shell commands and write to the filesystem via the TAO entrypoint defined in 'references/skill_info.yaml'.
  • Sanitization: There is no evidence of content sanitization or validation for the ingested JSON data in the skill's instructions or schemas.
  • [SAFE]: No hardcoded credentials, malicious obfuscation, or unauthorized network exfiltration patterns were detected. The use of 'encryption_key' parameters is documented as a standard tool configuration for model security.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 02:38 PM
Security Audit — agent-trust-hub — tao-train-nvpanoptix3d