remotion-video-production
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to manage project structures and execute rendering commands such as
npx remotion render. This is a standard part of the Remotion development workflow and is limited by the allowed-tools configuration. - [REMOTE_CODE_EXECUTION]: The skill uses
npxto execute the Remotion CLI. This involves fetching and running packages from the NPM registry at runtime. While these are well-known tools, they represent the execution of code fetched from an external repository. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it transforms user-provided natural language instructions directly into executable React components without explicit sanitization or boundary markers.
- Ingestion points: User instructions for video specifications and scene content are provided as natural language prompts.
- Boundary markers: None identified; there are no instructions to the agent to escape or isolate user input within the generated code templates.
- Capability inventory: The skill has access to the
Bashtool to write files and execute commands (npx), which allows generated code to be run in a local Node.js environment during the rendering process. - Sanitization: No sanitization or validation logic is present to ensure that user input does not contain malicious code snippets or logic that could be executed during rendering.
Audit Metadata