agentmemory-rest-api

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow exposes an HTTP REST surface where arbitrary outsider-authored text can be submitted directly via POST http://localhost:3111/agentmemory/remember (and similar ingest endpoints), and that text is then available for LLM recall/search through endpoints like POST /agentmemory/smart-search without requiring the agent to first select a specific trusted item.