company-intel

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

• Third-party content exposure detected (high risk: 0.78). The required workflow uses live web search to gather and cite information (e.g., investor pages, product pages, patent databases, job aggregators, news), and those fetched public pages can contain outsider-authored free text that the agent ingests into the LLM context for summarization/analysis—creating indirect prompt-injection exposure.