video-hyperframes

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches styling from Tailwind CSS CDN and typography from Google Fonts. Both are well-known technology services.\n- [COMMAND_EXECUTION]: Generates client-side JavaScript for frame navigation, playback control, and progress tracking within the HTML preview environment.\n- [PROMPT_INJECTION]: Ingests and processes untrusted user data for interpolation into HTML structures and JavaScript metadata, creating a surface for indirect prompt injection.\n
  • Ingestion points: User content determines the density and text of the generated frames as described in SKILL.md.\n
  • Boundary markers: No delimiters or explicit instructions to ignore embedded instructions are present in the template.\n
  • Capability inventory: Generates HTML and JavaScript that are executed within the agent's video preview surface.\n
  • Sanitization: There is no evidence of escaping or validation of user-provided content before it is rendered.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 07:23 PM