linkedin-leads

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text is ingested via the runtime scraping of LinkedIn content seeded by Google: search_site returns post URLs, then get_post and get_post_reactors fetch the post body and reactor names from third-party authors on LinkedIn, which the agent then places into the LLM context for orchestration/qualification.