designing-canvas-images

Warn

Audited by Snyk on Mar 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill includes a web-image search tool (search_images_to_canvas) described in reference/image-search.md that "search[es] images from the web and automatically download[s] and add[s] them to canvas," meaning the agent fetches open/public third-party images and uses them as reference content that can directly affect subsequent prompts and actions (e.g., generate_images_to_canvas), so untrusted third-party content can materially influence behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 02:37 AM
Issues
1