client-onboarding

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly performs runtime “Web search + web fetch” and “linkedin-profile-post-scraper” (outsider-authored public web/LinkedIn content) whose extracted text is written into client intelligence markdown files and then later read for Phase 2 synthesis, so that free text can enter the agent’s LLM context via those generated outputs.