launch-video

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx remotion to render video frames and export final MP4 files in various aspect ratios.
  • [COMMAND_EXECUTION]: It references and executes local helper scripts located in the scripts/ directory (contact-sheet.sh and probe-mp4.sh) to verify the fidelity and technical specifications of the rendered media.
  • [EXTERNAL_DOWNLOADS]: The use of npx remotion involves fetching the Remotion package and its dependencies from the official npm registry, which is a standard developer workflow.
  • [PROMPT_INJECTION]: The skill processes user-provided metadata (product names, taglines, CTAs) into video properties. While this represents a data ingestion surface, the context of video rendering using fixed templates significantly limits any risk of indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 10:32 AM
Security Audit — agent-trust-hub — launch-video