remotion-explainer-video
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches component catalogues and documentation from the vendor's official domain at snapcn.dev.
- [COMMAND_EXECUTION]: Utilizes shell commands via
npxto install external React components (shadcn add), execute the video rendering engine (remotion render), and set up the Snapcn Model Context Protocol (MCP) server. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text scripts to generate video content, creating a surface for indirect prompt injection if the input contains malicious instructions targeting the rendering environment.
- Ingestion points:
SKILL.mdworkflow instructs the agent to pass user input into component properties (e.g.,script,statuses,word) within generated React code. - Boundary markers: Absent. The instructions do not define delimiters or specify that the agent should ignore instructions embedded within the user's video script.
- Capability inventory: The skill environment possesses the ability to write executable React code and run shell commands through the
npxpackage runner. - Sanitization: Absent. No filtering or validation of the user-provided text is performed before it is placed into the code templates.
Audit Metadata