figma-implement-design

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the OpenAI skills repository as the source for the implementation workflow.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its reliance on external design data retrieved from user-provided Figma URLs.
  • Ingestion points: Untrusted data enters the agent's context through the Figma URL and the design context retrieved via the get_design_context tool.
  • Boundary markers: The instructions do not provide explicit delimiters or instructions to the agent to disregard potential instructions hidden within the design metadata or content.
  • Capability inventory: The skill directs the agent to write production code and download assets to the local file system, which are sensitive operations.
  • Sanitization: There are no requirements for sanitizing or escaping content retrieved from the design before it is used to generate code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 03:00 PM
Security Audit — agent-trust-hub — figma-implement-design