mem0-cli

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflows (see references/workflows.md — notably "Agent Mode for LLM Consumption" and the "Multi-User Agent Pattern") explicitly show the agent calling mem0 search/list/get against the Mem0 platform (https://api.mem0.ai) to fetch user-generated memories, which the agent is expected to read and use to decide actions, so untrusted third‑party content can indirectly inject instructions.