linkfox-multimodal-recognize-image

Warn

Audited by Snyk on Apr 8, 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 public image URLs and "downloads the image" for multimodal analysis (see SKILL.md "provide a publicly accessible image URL" and scripts/multimodal_recognize_image.py which calls the tool gateway), so untrusted third‑party visual content could be interpreted and influence the agent's outputs or actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 8, 2026, 07:16 AM
Issues
1