figma-annotations

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and processing designer-authored text from Figma nodes.
  • Ingestion points: User-controlled labels and markdown descriptions are retrieved from node annotations in scripts/get-annotations.js.
  • Boundary markers: The skill lacks delimiters or instructions to isolate external annotation content, potentially allowing embedded instructions to influence the agent.
  • Capability inventory: The skill can modify Figma node annotations and categories, providing an automated vector for design manipulation.
  • Sanitization: There is no evidence of sanitization or validation of the text strings fetched from the Figma Plugin API before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:56 AM
Security Audit — agent-trust-hub — figma-annotations