bs-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 performs runtime public-web research (e.g., “Use original pages from… public discussions… GitHub issues… job posts… marketplace pages”), which means outsider-authored free text from fetched pages/issues is ingested into the agent’s LLM context for evidence extraction and qualification.