skills/johnlindquist/claude/figma/Gen Agent Trust Hub

figma

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Provides automated scripts using curl, jq, and bun for interacting with the Figma API and managing local design assets.
  • [EXTERNAL_DOWNLOADS]: Recommends the installation of @figma-export/cli and its plugins from the npm registry to handle component exports.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches node data from the Figma API (an external source) and transmits it to an LLM (gemini -m pro) for code generation, creating a potential attack surface if design content or metadata contains adversarial instructions intended to influence the AI's output.
  • [DYNAMIC_EXECUTION]: Employs an AI model to dynamically generate React component code and styles based on design data retrieved from Figma at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:25 PM
Security Audit — agent-trust-hub — figma