web-search-api

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to probe and query public SearXNG instances (via https://searx.space/data/instances.json and instance endpoints like https://searx.party/search?q=...) and to ingest results[].content from those open web search results, which are untrusted third‑party/user‑generated content that the agent is expected to read and act on.