first-customer-finder

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly instructs the agent to “Search current public sources” and “Prefer original pages over search snippets,” meaning outsider-authored free text from runtime-fetched public web pages (and other public community posts/issues) is ingested into the agent’s LLM context for research/qualification.