exa-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's research and search commands (e.g., exa-ai research-start, exa-ai search, webset-create, and get-contents) explicitly read and ingest web pages/"page read" results and webset/search results from public third‑party sources, so the agent will consume untrusted user-generated/open web content as part of its workflow.