cloud

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

• Third-party content exposure detected (high risk: 0.80). The skill reads and persists user-generated conversation content from the assistant-cloud backend (e.g., cloud.threads.messages.list, cloud.threads.get/create and message "content"/"source" fields in references/persistence.md), so the agent will ingest untrusted third-party/user-provided content that could carry indirect prompt injections.