verify-trend-report

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

• Third-party content exposure detected (high risk: 0.72). Outsider free text can enter the LLM context via cogni-claims (Phase 2) when it “fetches source URLs” from the claims’ cited URLs and then produces per-claim verification details consumed in later steps (Phase 3 prompt content and Phase 4 revisor prompt inputs), creating an indirect prompt-injection surface from public web content.