create-property

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses figma_execute and use_figma to run JavaScript logic for document manipulation within the Figma design tool. This is a core functionality but involves executing scripts in a design-focused sandbox.\n- [PROMPT_INJECTION]: There is a potential for indirect prompt injection through data extracted from Figma.\n
  • Ingestion points: Component names, variant property names, and definitions are read from external Figma files provided by the user (SKILL.md, Step 4).\n
  • Boundary markers: The skill does not use explicit delimiters or instructions to help the agent distinguish between component data and instructions.\n
  • Capability inventory: The agent has the ability to modify Figma documents, create new layers, and take screenshots using figma_execute across several workflow steps.\n
  • Sanitization: Extracted data is not validated or sanitized for injection patterns before being processed by the agent or used in template substitutions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 10:11 PM
Security Audit — agent-trust-hub — create-property