canvas-designer

Warn

Audited by Snyk on May 9, 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 explicitly performs web image ingestion via the search_canvas_images tool ("Search images from the internet and automatically download and add them to the canvas" in reference/image/image-search.md and SKILL.md), meaning the agent fetches and uses untrusted, user-generated/open-web content as inputs that can directly influence generation and subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 9, 2026, 07:22 AM
Issues
1