searxng-search

Warn

Audited by Snyk on Mar 9, 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 queries a SearXNG instance (configured via base_url in ~/.config/agents/searxng.json) and directly ingests/parses JSON search results (answers, infoboxes, results/content) that originate from arbitrary public websites, so untrusted third‑party content is read and presented and could influence subsequent agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 12:36 PM