searxng-search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill instructs agents to call the local SearXNG API (e.g. http://localhost:8888/search?q=...&format=json) and to parse .results/.content coming from public third‑party sources (web pages, GitHub, Stack Overflow, npm, arXiv, Docker Hub, etc.), so the agent will ingest and interpret untrusted, user-generated/open-web content.