interior-design-visualization

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md Quick Start and multiple Use Case Examples require supplying arbitrary public image_urls (e.g., "image_urls": ["https://example.com/my-living-room.jpg"]) which the agent ingests and interprets to drive redesign decisions (and the SSE docs also describe web_search/web_search_citations returning public URLs), so untrusted third‑party content can materially influence tool behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 07:57 AM