multi-cloud-security-posture

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s required workflow is to aggregate security findings from cloud provider APIs and third-party CSPM integrations (e.g., Wiz/Prisma/Orca), which at runtime will ingest outsider-authored free-text fields like finding descriptions from those external systems into the agent’s LLM context.