mem0

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md describes retrieving and searching user memories from the Mem0 public API (e.g., "POST /v1/memories/search/" and "GET /v1/memories/?user_id="), which ingests and returns untrusted, user-generated content that the agent is expected to read and use to influence behavior.