cargo-content

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via connector-backed libraries: cargo-ai content library create syncs external documents (help center/knowledge base) through an extractor, and those synced document texts are then available for RAG grounding in the agent’s LLM context.