content-video

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill logic is focused on content generation and scaffolding. It utilizes local project files for branding and provides well-structured templates for the Remotion video framework.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data to generate video scripts and code compositions, creating a potential surface for indirect injection.
  • Ingestion points: User-supplied topics, messages, and audience descriptions in SKILL.md; local branding files in the brand/ directory.
  • Boundary markers: No specific delimiters or instructions to treat input as untrusted are implemented in the generation flow.
  • Capability inventory: The skill generates markdown storyboards and TSX source code for the Remotion framework.
  • Sanitization: The skill does not define methods for sanitizing or escaping user-provided strings before they are used in script or code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:25 AM
Security Audit — agent-trust-hub — content-video