AGENT LAB: SKILLS

figma-automation

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill fetches and ingests user-generated Figma content (files, comments, components, projects) from arbitrary Figma URLs via endpoints like FIGMA_DISCOVER_FIGMA_RESOURCES, FIGMA_GET_FILE_JSON, FIGMA_GET_COMMENTS_IN_A_FILE, and FIGMA_GET_FILES_IN_A_PROJECT, so the agent would read untrusted third‑party content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill requires connecting at runtime to the Rube MCP endpoint https://rube.app/mcp and to call RUBE_SEARCH_TOOLS to fetch current tool schemas, which directly control the agent's prompts/tool behavior and can therefore alter/execute actions remotely.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:21 PM