ai-supply-chain-bottleneck-hunter

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text via the evidence/sources fields (e.g., earnings-call transcripts, press releases, industry articles) that are then rendered into LLM-readable markdown (render_evidence_trace, render_evidence_memo, render_quick_scan) and included in the agent context; this is outsider content because it is authored by companies/industry media other than the operating user.