tao-finetune-video-clip
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes video metadata in JSON format (vadr1_chunks) for training and inference, which constitutes a surface for processing untrusted data.
- Ingestion points: Files specified in
dataset.train.video_text.metadataanddataset.val.video_text.metadata(SKILL.md, references/spec_template_train.yaml). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the input metadata.
- Capability inventory: The skill executes training and inference actions via Docker containers.
- Sanitization: No explicit validation or filtering of the textual content in the metadata JSON is provided.
- [EXTERNAL_DOWNLOADS]: Fetches model weights and training datasets from vendor-controlled infrastructure.
- Uses
s5cmdto mirror assets from a vendor internal S3 endpoint (pdx.s8k.io). - Pulls container images from the vendor's official Container Registry (
nvcr.io). - [DYNAMIC_EXECUTION]: The skill instructs the agent to set
TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1, which disables PyTorch'sweights_onlyunpickling security check. - Evidence: This configuration is used in the
DOCKER_COMMONenvironment variables inSKILL.mdand referenced ineval.config. - Context: This is documented as a requirement for compatibility with specific model checkpoints but reduces protection against malicious pickle data if non-vendor models are loaded.
Audit Metadata