qwen-mm-plugins-edu-agent
Warn
Audited by Snyk on Aug 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Step 0 reads the user-provided math problem by extracting “complete problem text” from images in the user-controlled
image_assets/folder via the Read tool, and that extracted free text is then used as primary input for subsequent LLM steps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata