video
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read context from external files such as .agents/product-marketing.md or .claude/product-marketing.md. 1. Ingestion points: Reads from project-level marketing context files (.agents/product-marketing.md, .claude/product-marketing.md, product-marketing-context.md). 2. Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are mentioned for the external context files. 3. Capability inventory: The skill instructs the agent to generate code (Hyperframes/Remotion) and interact with external video generation APIs. 4. Sanitization: No sanitization or escaping of the ingested marketing context is specified before interpolation into instructions or code generation.
- [COMMAND_EXECUTION]: The skill instructions include commands for installing and initializing video projects. Evidence: 'npm install hyperframes' and 'npx create-video@latest' are suggested for initializing programmatic video projects. These are standard developer operations for the mentioned tools.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and official websites for several well-known video production services. Evidence: Provides links to remotion.dev, runwayml.com, and heygen.com for tool documentation and pricing.
Audit Metadata