tao-generate-video-reasoning-annotations
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
auto_labelcommand-line utility to run the annotation pipeline steps, as defined inSKILL.mdandreferences/skill_info.yaml. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it processes untrusted video data and provides the output to a VLM for reasoning. Instructions or text appearing in the video frames could theoretically override the agent's intended annotation behavior.
- Ingestion points: Raw video files accessed via the
video_rootorinput_jsonl_filesparameters specified inSKILL.md. - Boundary markers: None are defined to differentiate between video content and annotation instructions within the frames.
- Capability inventory: Subprocess execution of the
auto_labeltool and network requests to third-party VLM/LLM providers like Google Gemini or OpenAI-compatible endpoints (references/configuration.md). - Sanitization: There is no documented mechanism to sanitize or filter potential instructional text embedded within the visual content of the source videos.
Audit Metadata