prompt-guard

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and scans untrusted third-party content (see "Filter API responses and RAG documents", the api_response example, and the batch_filter_documents RAG filtering workflow) so the agent would read/interpret arbitrary web/API/RAG documents that could carry indirect prompt injections.