remotion-compose
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural-language video briefs to generate React/TypeScript code and perform filesystem operations.
- Ingestion points: The agent ingests a "natural-language video brief" from the user (Step 1), including duration, scenes, brand colors, and copy.
- Boundary markers: The instructions lack explicit boundary markers or system instructions to the agent to treat the user's brief as data only and ignore any embedded instructions.
- Capability inventory: The skill is designed to write new files to the filesystem (
src/compositions/<VideoName>.tsx) and modify existing project files (src/Root.tsx). - Sanitization: There are no requirements for the agent to sanitize, escape, or validate the user-provided copy, brand settings, or scene descriptions before interpolating them into code templates or using them for file naming.
Audit Metadata