agentmemory-mcp-tools

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow exposes and ingests arbitrary outsider-authored free text via the memory_save/memory_slot_* tool parameters (content, text) and later LLM-readable retrieval via tools like memory_smart_search/memory_recall, so an outsider who can submit those fields can poison what the agent reads back.