design-to-component

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Figma designs, which could potentially contain malicious instructions intended to influence the agent's behavior during code generation or file system operations.
  • Ingestion points: Data is ingested from external Figma files through MCP tools, specifically figma_get_metadata (component names/descriptions) and figma_get_design_context (layer names and properties) in SKILL.md.
  • Boundary markers: The skill does not define clear delimiters or provide instructions to the agent to ignore natural language instructions that might be embedded within Figma component descriptions or variable names.
  • Capability inventory: The agent has the capability to generate code, write files to the local filesystem (scaffolding components), and potentially execute browser automation tools for visual validation.
  • Sanitization: There is no evidence of sanitization or filtering logic applied to the text content retrieved from the Figma API before it is used to generate component logic and file structures.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 01:52 PM
Security Audit — agent-trust-hub — design-to-component