vendor-risk-kyc-screening

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

• Third-party content exposure detected (high risk: 0.85). The workflow explicitly instructs the agent to “search and extract” from external web sources (e.g., regulators, sanctions pages, court records, credible news) and then ingest extracted page text into the LLM context, which is outsider-authored free text at runtime.