figma-use-cli
Warn
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's setup instructions direct users to install the figma-use package globally from the npm registry.
- [COMMAND_EXECUTION]: The figma-use render command dynamically executes logic from local .tsx or .jsx files to generate Figma nodes. This involves runtime processing of code-defined design structures.
- [COMMAND_EXECUTION]: The skill requires launching the Figma application with the --remote-debugging-port=9222 argument, enabling programmatic control of the running process.
- [PROMPT_INJECTION]: The skill processes untrusted design data via stdin and local files during the rendering process, creating an indirect prompt injection surface.
- Ingestion points: figma-use render --stdin, figma-use render [file].tsx.
- Boundary markers: None specified to delimit user-provided design code.
- Capability inventory: Subprocess calls via figma-use CLI, file system writes via figma-use export.
- Sanitization: No evidence of input validation for JSX content.
Audit Metadata