tao-generate-video-reasoning-annotations
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
auto_labelcommand-line utility from the NVIDIA TAO Toolkit within a Docker container environment to orchestrate the video annotation pipeline. This is the primary and expected function of the skill. - [EXTERNAL_DOWNLOADS]: The pipeline interacts with external vision-language model (VLM) and large language model (LLM) providers, specifically Google Gemini and OpenAI-compatible endpoints, to perform video analysis and text generation. These are well-known, trusted services required for the skill's operation.
- [CREDENTIALS_UNSAFE]: The documentation provides instructions for managing API keys (e.g.,
GOOGLE_API_KEY). It correctly advises users to set these as environment variables or within configuration files, which is a standard and secure practice for managing developer secrets.
Audit Metadata