NYC

figma-designer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill ingests data from external Figma files which are attacker-controlled sources. Maliciously crafted text layers or component descriptions in Figma could attempt to influence the agent's PRD generation or code output. \n
  • Ingestion points: Data fetched via figma_get_file, figma_get_nodes, and figma_get_components tools. \n
  • Boundary markers: None identified in the provided templates to distinguish Figma content from system instructions. \n
  • Capability inventory: The skill facilitates the generation of technical specifications and code snippets, which are subsequently used by implementation skills. \n
  • Sanitization: No evidence of data sanitization or validation of the ingested Figma content is present in the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM