exa-lead-gen

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

• Third-party content exposure detected (high risk: 0.85). High: the required workflow calls exa-deep__deep_search_exa (public web deep search) with free-form objective/systemPrompt, and Exa typically ingests and returns scraped third-party page text into the model context, creating an indirect prompt-injection path from outsider-authored web content.