cyber-diligence-governance

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the “Questionnaire and evidence review” and “Vendor and TPRM assessments” workflows when the agent ingests inbound target/vendor questionnaire responses, supplemental questions, and evidence excerpts (e.g., customer/third-party portal text) to map and summarize findings.