general-video
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
npx hyperframesCLI and local Node.js scripts to manage the video production lifecycle. This includes initializing projects, verifying authentication status, and running validation tools likelintandcheck. - [EXTERNAL_DOWNLOADS]: The skill uses
npx hyperframes skills updateto maintain currency andnpx hyperframes catalogto fetch configuration and assets from a hosted registry. These operations are handled by the vendor's official toolset and follow expected maintenance patterns. - [INDIRECT_PROMPT_INJECTION]: The workflow ingests data from
BRIEF.md,STORYBOARD.md, and external Figma URLs. This untrusted content influences the generated composition and instructions for sub-agents. The skill includes a dedicated Figma adapter for sanitization, but lacks explicit adversarial delimiters for markdown-based project briefs. - [DYNAMIC_EXECUTION]: The packet generation scripts dynamically assemble context and roles for sub-agents by concatenating script fragments and storyboard data at runtime. This allows for modular and parallel build processes controlled by the orchestrator.
Audit Metadata