buyer-persona-generator

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the required workflow runs research_company.py, which fetches public same-domain pages (homepage + discovered pricing/about/customers/case-studies/etc.) and extracts their visible text into company_bundle.json; this is outsider-authored free text from the company’s website (public web content) that the agent then reads and includes in LLM context for persona synthesis.