multi-search

Warn

Audited by Snyk on Mar 1, 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 performs web searches and scrapes arbitrary public webpages (see SKILL.md/README examples and multi_search.py: search -> fetch_web_content / fetch_search_results_content and WebContentFetcher.fetch which GETs and parses external URLs), so untrusted third-party content from open websites is ingested and then used (e.g., for summarization), enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:01 PM