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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata