memo-api

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

• Third-party content exposure detected (high risk: 0.80). The skill directly fetches user-generated, potentially untrusted content from the MaiMemo API (e.g., GET /notepads returns notepad "content" in references/notepads-api.md and GET /notes, /phrases, /interpretations and study endpoints return user-created text) and the SKILL.md workflows (Multi-domain Workflow Hints and Study Usage Scenes) require the agent to read those responses and use them to decide or drive follow-up actions (create/update notepads, notes, exports), so third-party content could materially influence agent behavior.