searxng
Warn
Audited by Snyk on Mar 3, 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). This skill runs a local SearXNG metasearch (SKILL.md "Privacy-respecting web search" / "aggregates results from 70+ search engines") and the runtime script (scripts/search.py) POSTs queries to the SearXNG /search JSON API and parses titles, descriptions and infobox suggestions from arbitrary public websites, meaning untrusted third‑party content is ingested and returned as part of the agent's workflow.
Audit Metadata