general-video

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the npx hyperframes and node commands to perform essential tasks such as project initialization, linting, authentication checks, and the orchestration of video frame generation. These operations are scoped to the HyperFrames toolchain and are necessary for the skill's primary function.
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to update its own capabilities via npx hyperframes skills update. These updates are retrieved through the standard NPM registry and are consistent with vendor-provided maintenance procedures.
  • [PROMPT_INJECTION]: The skill processes user-supplied data in BRIEF.md and STORYBOARD.md, presenting a surface for indirect prompt injection.
  • Ingestion points: Video briefs, storyboards, and design configuration files (frame.md, design.md).
  • Boundary markers: Employs structured markdown headers and delimiters to define scene boundaries.
  • Capability inventory: Shell command execution (npx, node) and file system access for project management.
  • Sanitization: Instructions mandate SVG sanitization for external assets and use specific adapters for Figma content to ensure security.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 03:03 AM
Security Audit — agent-trust-hub — general-video