tao-validate-dataset-format
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external datasets, which introduces a surface for indirect prompt injection if the datasets contain malicious metadata or instructions.
- Ingestion points: The skill ingests untrusted data from the directory or file specified via the
--pathargument during the execution oftao-daft validate. - Boundary markers: The instructions do not provide explicit boundary markers or instructions to ignore embedded content within the processed datasets.
- Capability inventory: The skill leverages the
Bashtool to execute the validation command and requires access to the local file system to read dataset files. - Sanitization: There is no mention of input sanitization or content filtering for the data being validated within the skill's instructions.
- [EXTERNAL_DOWNLOADS]: The skill documentation prescribes the installation of a Python dependency.
- Evidence: Instructions in
SKILL.mdandskill-card.mdrecommend runningpip install nvidia-tao-daftto install the necessary validation tools. - Note: The
nvidia-tao-daftpackage is a resource provided by the vendor (NVIDIA) for use with their TAO Toolkit.
Audit Metadata