image-editor

Warn

Audited by Snyk on Feb 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.md explicitly accepts arbitrary image_urls (URLs of images to edit) and includes an enable_web_search option ("Grounds editing in current web data"), so the agent will fetch and interpret untrusted third-party web content as part of its editing workflow, which could allow indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 08:22 AM