figma-skill

Warn

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and metadata direct the agent or user to install a package from an unverified external source (nafiurrahmanniloy/figma-skill) using the npx skills add command. This pattern involves executing code from a third-party developer not associated with the provided trusted vendors list.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process Figma Community resources, which are untrusted external inputs. This creates a surface for indirect prompt injection where malicious instructions could be embedded in design files.
  • Ingestion points: Figma Community resources extracted via the Figma API.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are documented for the processing of these external resources.
  • Capability inventory: The skill possesses code generation capabilities and the instructions explicitly mention the use of the ! shell execution command in Claude Code.
  • Sanitization: There is no evidence of sanitization, filtering, or validation performed on the design tokens or resources before they are used for code generation or context building.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 25, 2026, 06:33 PM
Security Audit — agent-trust-hub — figma-skill