exa-unified-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and ingest open/public third-party content via web_search_advanced_exa (see SKILL.md and references such as references/company-research.md and references/tweet-search.md which target public websites, LinkedIn-style profiles, blogs/portfolios, tweets, arXiv/academic pages, and SEC filings), so untrusted user-generated or public web content is read and used to drive the agent's analysis and actions.