background-removal

Warn

Audited by Snyk on Apr 2, 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 accepts arbitrary image URLs in SKILL.md (e.g., the "image_urls" fields in the Quick Start and examples) and its SSE docs include web_search_query/web_search_citations events, showing the agent will fetch and consume open web content (images and search results) that are untrusted and can influence processing and tool decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 02:04 AM
Issues
1