finding-triage

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

• Third-party content exposure detected (medium risk: 0.65). The workflow is a triage/disposition generator that consumes “findings from any source” (e.g., scanner/audit reports, issue/PR text, vendor disclosures), and at runtime it would ingest outsider-authored free-form finding content into the agent’s LLM context via the “Any audit skill — this consumes their findings as input” boundary.