remotion
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to scaffold new projects via 'npx create-video', install dependencies with 'npm install', and start a local Remotion Studio server using 'npm run studio'. These are standard actions for Remotion development.
- [EXTERNAL_DOWNLOADS]: It downloads necessary packages from the NPM registry and interacts with established external services such as Mapbox and ElevenLabs. These dependencies and API calls are aligned with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it incorporates external data into code generation.
- Ingestion points: The agent reads user-provided video descriptions and existing project files like 'Root.tsx'.
- Boundary markers: No delimiters or isolation instructions are present to prevent the agent from following instructions embedded in the ingested data.
- Capability inventory: The skill is capable of writing to the file system, installing new packages, and executing shell commands.
- Sanitization: No explicit sanitization or validation logic is applied to the input data before it is used to generate or modify components.
Audit Metadata