video

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external video content and social media posts to assist in script writing and video production.
  • Ingestion points: The skill uses tools like watch-video to process transcripts and video frames and social-fetch to retrieve external post data and media URLs, as outlined in references/edit-anatomy.md.
  • Boundary markers: The instructions do not define explicit boundary markers or delimiters when interpolating data from external transcripts or social posts into the agent's prompts.
  • Capability inventory: The skill generates executable code for Hyperframes (HTML/CSS) and Remotion (React) and facilitates package management operations via npm and npx.
  • Sanitization: The skill does not explicitly describe sanitization or filtering logic for content extracted from external video references before it is processed by the AI.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation and use of official programmatic video libraries and service APIs.
  • Recommends the installation of the hyperframes package from the npm registry, which is an open-source library from HeyGen.
  • Recommends using npx create-video for setting up Remotion, a well-known programmatic video framework.
  • References official API documentation for trusted technology providers including Google (Veo), OpenAI (Sora), and Runway.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 03:04 PM