create-anatomy
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill dynamically generates and executes JavaScript code within the Figma environment using
figma_executeanduse_figma. It interpolates data extracted from the Figma canvas (such as component names and property definitions) into script templates.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Malicious content within a Figma file (e.g., a component or layer name designed to break out of a JavaScript string literal) could influence the execution of subsequent scripts if the agent does not properly sanitize the input before interpolation.\n - Ingestion points:
uspecs.config.jsonand Figma design data including layer names, properties, and values.\n - Boundary markers: The skill lacks explicit sanitization or boundary markers (such as character escaping) to isolate untrusted design data within the script templates.\n
- Capability inventory: The skill possesses capabilities to execute JavaScript (
figma_execute), navigate files (figma_navigate), and capture visual output (figma_take_screenshot).\n - Sanitization: No explicit sanitization or validation of strings fetched from the Figma API is performed before they are embedded into executable code blocks.
Audit Metadata