lead-research-assistant

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

• Third-party content exposure detected (high risk: 0.70). The required workflow includes “Search for companies matching the criteria” and “Look for signals of need (job postings, tech stack, recent news)”, which at runtime would typically require fetching/reading outsider-authored web content (public pages/news/job posts) and injecting that free text into the agent’s LLM context.