figma-automation

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to utilize a remote MCP server hosted at https://rube.app/mcp to access the Figma toolkit.
  • [PROMPT_INJECTION]: The skill processes untrusted data from Figma files and comments, creating a potential surface for indirect prompt injection.
  • Ingestion points: Data is ingested from external sources through tools like FIGMA_GET_FILE_JSON and FIGMA_GET_COMMENTS_IN_A_FILE (SKILL.md).
  • Boundary markers: The instructions do not define boundary markers or delimiters to isolate untrusted data from the agent's instructions.
  • Capability inventory: The skill has the capability to read design files, extract tokens, render images, and write comments back to Figma files via various FIGMA_* tools.
  • Sanitization: No sanitization or validation logic is present to filter malicious instructions embedded in Figma design files or user comments.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 04:38 PM
Security Audit — agent-trust-hub — figma-automation