figma-generate-design

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an indirect prompt injection attack surface because it ingests and interprets untrusted source code and SVG data from the user's repository to inform design generation.
  • Ingestion points: Project source files (*.tsx, *.js, *.kt, *.swift) and SVG assets located in the codebase.
  • Boundary markers: The instructions lack specific boundary markers or instructions to the model to ignore embedded malicious directions in the analyzed code.
  • Capability inventory: The skill possesses capabilities to execute JavaScript via use_figma, capture UI via generate_figma_design, and generate/upload assets.
  • Sanitization: No specific sanitization or filtering of the extracted code or SVG content is described before processing.
  • [DYNAMIC_EXECUTION]: The skill dynamically generates JavaScript code to be executed via the use_figma tool. These scripts incorporate data extracted from the user's project, such as component identifiers and SVG strings, creating a potential path for script injection if the source data is maliciously crafted.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:44 PM