content-extraction

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). This skill's SKILL.md explicitly instructs the agent to crawl a user-provided website URL (see "Extraction Process" Step 1: Discover all pages and Step 2: Extract content per page), downloading and parsing DOM, images, forms, and other public site content—untrusted third-party data that is consumed and output as structured files which can materially influence downstream agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 08:27 AM