NYC

figma-generate-component

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (MEDIUM): The skill processes untrusted external content from Figma designs, creating an Indirect Prompt Injection surface.
  • Ingestion points: Design structure, layer names, and component properties retrieved via the Figma MCP server (SKILL.md).
  • Boundary markers: Absent. The skill does not define delimiters or provide 'ignore embedded instructions' warnings for the data retrieved from Figma.
  • Capability inventory: The skill generates production-ready code (React, Vue, HTML/CSS), which can lead to the injection of backdoors or malicious scripts into a user's codebase.
  • Sanitization: There is no evidence of sanitization or validation of the text and metadata extracted from Figma before it is interpolated into the code generation prompt.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:01 PM