figma-generate-library

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external codebase data (such as design tokens and configuration files) to automate Figma library construction, creating a surface where malicious instructions in those files could attempt to influence agent behavior.\n
  • Ingestion points: references/discovery-phase.md describes analyzing codebase files like *.tokens.json, CSS variables, and Tailwind configurations.\n
  • Boundary markers: No specific delimiters or safety instructions are defined for processing external codebase content.\n
  • Capability inventory: The skill utilizes the use_figma tool, which allows the agent to create and modify pages, variables, and components in Figma.\n
  • Sanitization: The skill does not describe explicit sanitization for data extracted from codebase files before use in Figma API calls.\n- [DYNAMIC_EXECUTION]: The skill generates and executes JavaScript scripts for the Figma API based on provided templates and logic.\n
  • Evidence: The skill uses use_figma to execute JavaScript generated from local templates and extracted tokens, as detailed in the scripts/ folder and references/component-creation.md. This is the intended functional mechanism of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:08 PM
Security Audit — agent-trust-hub — figma-generate-library