video-hyperframes

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-supplied text into HTML frame templates without defining boundary markers or sanitization logic.\n
  • Ingestion points: User content is ingested to populate the text of video frames as described in SKILL.md.\n
  • Boundary markers: No explicit delimiters are used to separate user data from the template instructions.\n
  • Capability inventory: The agent generates HTML and JavaScript files.\n
  • Sanitization: The instructions do not specify any escaping or validation for user-provided strings.\n- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate and embed functional JavaScript for UI behavior.\n
  • Evidence: SKILL.md contains a requirement to add a JavaScript block for automatic playback and frame control, which is implemented in example.html.\n- [EXTERNAL_DOWNLOADS]: The sample output references resources from well-known service providers.\n
  • Evidence: example.html includes links to the Tailwind CSS CDN (cdn.tailwindcss.com) and Google Fonts API (fonts.googleapis.com).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 10:38 AM