extract-and-export

Warn

Audited by Snyk on Mar 10, 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). The skill explicitly crawls and downloads arbitrary public websites via start_crawl({ url: "$0" }) and runs extract_site() to produce structured page content (notably the "extracted" format "for AI consumption"), so the agent ingests untrusted third-party web content that could contain instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 01:38 AM