agentmemory-rest-api

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can be ingested via the REST endpoints that accept user-provided content/query fields (e.g., POST /agentmemory/remember and POST /agentmemory/smart-search), and that text is then stored/recalled into the agent’s LLM context; the skill does not restrict the source of that text to the operating user.