searxng-api

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

• Third-party content exposure detected (high risk: 0.90). The skill calls a SearXNG Search API endpoint (SEARXNG_BASE_URL, e.g. GET /search?q=...&format=json) and parses the returned results, answers, suggestions, and infoboxes, which are aggregated from public websites and user-generated sources on the open web and therefore constitute untrusted third-party content the agent will read and interpret.