tao-train-deformable-detr
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows standard procedures for training and deploying AI models using the NVIDIA TAO Toolkit. It uses official container images from
nvcr.io, which is a trusted source for this vendor. - [EXTERNAL_DOWNLOADS]: The skill references official NVIDIA container images (
nvcr.io/nvstaging/tao/tao-toolkit-pytandnvcr.io/nvstaging/tao/tao-toolkit-deploy). These references are documented neutrally as part of the required infrastructure for model training and deployment. - [INDIRECT_PROMPT_INJECTION]: The skill processes external datasets (COCO format) provided by the user. While this represents a data ingestion surface, it is a primary functional requirement for model training, and the risks are minimal as the processing occurs within isolated container environments.
- [SAFE]: No hardcoded credentials, malicious persistence mechanisms, or unauthorized privilege escalation attempts were found. Cryptographic signatures provided in the skill bundle are used for integrity verification and do not contain hidden malicious code.
Audit Metadata