demo-video
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill includes explicit safety instructions to remove secrets and personal information (PII) during product capture phases, demonstrating a focus on data privacy.
- [COMMAND_EXECUTION]: The skill references standard Remotion CLI commands (e.g.,
npx remotion render,npx remotion studio) for generating video assets. These are standard operations for the Remotion framework and occur within the user's project environment. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a broad ingestion surface for external data (product UI, documentation, and existing media) to establish a video brief.
- Ingestion points: Product UI, documentation, brand assets, and existing media (SKILL.md).
- Boundary markers: The instructions do not explicitly define delimiters for untrusted documentation text, though they emphasize manual verification and scripting.
- Capability inventory: The agent has the ability to write Remotion source code and execute Remotion CLI tools to render video files.
- Sanitization: The skill mandates the scrubbing of sensitive data from visual captures, which serves as a mitigation for data exposure during the production process.
Audit Metadata