tao-train-optical-inspection
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes manufacturing datasets (CSV and image archives) which establishes an indirect prompt injection attack surface.\n
- Ingestion points: Data enters the context through
dataset.csvandimages.tar.gzas defined inSKILL.mdandreferences/skill_info.yaml.\n - Boundary markers: No explicit delimiters or safety instructions are used to distinguish untrusted data from instruction context.\n
- Capability inventory: The agent utilizes the
Read Bashtool and generates complexdocker runinstructions.\n - Sanitization: The instructions lack explicit validation steps for external data content before processing.\n- [COMMAND_EXECUTION]: The skill generates shell commands for managing Docker containers and ML tasks. It also provides guidance on using the
TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1environment variable to load trusted checkpoints, including appropriate safety warnings for untrusted artifacts.\n- [EXTERNAL_DOWNLOADS]: The skill references container images and repositories fromnvcr.ioandgithub.com/NVIDIA-TAO, which are official vendor resources and are treated as trusted sources.
Audit Metadata