figma-design-to-code

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to process external data from Figma (such as design annotations, notes, and node content) which is then used to influence the generation of source code.
  • Ingestion points: Design context is ingested via the get_design_context tool as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the design annotations.
  • Capability inventory: The skill allows for the creation and modification of files in the target project's codebase based on these inputs.
  • Sanitization: The workflow does not specify validation or sanitization steps for the data retrieved from the design tool before it is used for code synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 09:40 AM
Security Audit — agent-trust-hub — figma-design-to-code