image-fetcher

Warn

Audited by Snyk on Feb 16, 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 explicitly fetches and displays images from arbitrary URLs (see scripts/fetch_image.py and scripts/fetch_images_batch.py and the "Search Integration" / "For Chat Display" sections), which ingests untrusted third-party web content that the agent will download and present as part of its workflow, enabling potential indirect prompt injection via user-supplied or public-hosted images.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:34 AM