searxng
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: 0.80). The skill's CLI calls a configured SearXNG instance and ingests its live JSON search results (scripts/searxng.py: search_searxng uses httpx.get to SEARXNG_URL/search and display_results_table prints result snippets), and the README/SKILL.md explicitly permit using public SearXNG instances, so untrusted web content can be returned and influence agent outputs/decisions.
Audit Metadata