review-video

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use npx remotion to render video content and manage the development environment. These commands are standard for the Remotion framework.
  • [INDIRECT_PROMPT_INJECTION]: The skill uses feedback from an external video analysis tool to suggest code modifications.
  • Ingestion points: The fixes and priority_fix fields in the JSON output from the sync-analyse-video tool.
  • Boundary markers: The skill does not define specific prompt delimiters for the ingested analysis data.
  • Capability inventory: The agent has the ability to modify project source code and execute shell commands (npx remotion).
  • Sanitization: Human oversight is enforced; the agent is instructed to ask the user for confirmation before applying any suggested fixes.
  • [DATA_EXFILTRATION]: Local video renders are uploaded to TwelveLabs for AI-powered vision analysis. This is a core component of the intended video production workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:03 PM