memos-memory-guide

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to use skill_search(scope="public") and skill_get to discover and read other agents' "public" skills and to read/search/write "public" memories (e.g., memory_search, memory_write_public), which are untrusted, user-generated third‑party content the agent is expected to read and can materially change its actions.