默认模式网络（DMN）是模拟大脑发散性思维的自主思考系统。在用户无主动交互且系统空闲时触发，自动进行内部记忆整合、跨界创意碰撞、意义生成和引入批判性视角的自我辩论。适合在空闲时段自动深化知识库。

This skill tells the agent to read and write your notes, produce daily 'synthesis' files, and generate concrete engineering actions (clone repos, write demo scripts, append to an 'evolve' queue) — yet it declares no filesystem paths, permissions, or approval gates. Before installing, consider: 1) Do you want an autonomous background skill that can modify files and suggest/perform host-level engineering actions? 2) If yes, restrict its scope: configure the asset paths to dedicated sandbox directories (not your entire knowledge base), make them read-only where appropriate, and require manual approval for any action that would execute code or modify system repos. 3) Prefer to run it in a confined environment (container or VM) first to observe behavior. 4) Ask the publisher to explicitly declare required config paths and an approval flow (e.g., proposal-only unless you authorize execution), or to provide a mode that only writes outputs to a safe, user-designated folder and never auto-appends to evolution queues. Additional information that would raise confidence: an explicit permission model, declared config paths limited to user-chosen sandbox directories, and a mode that requires user confirmation before any host-level action (clone/run/write outside a sandbox).

Type: OpenClaw Skill Name: dmn-default-mode-network Version: 3.3.0 The skill explicitly grants the AI agent 'full host control privileges' and mandates 'Agentic Action Proposals' (SKILL.md, README.md, references/execution-flow.md). These proposals include direct host execution actions such as 'installing a GitHub project,' 'writing a Python verification script,' and 'cloning a GitHub repo' (assets/session-synthesis.md, references/execution-flow.md). Furthermore, the skill incorporates a 'self-evolution loop' where proposals for AI capability upgrades are automatically queued for future execution (README.md, references/execution-flow.md). While the stated purpose is self-improvement and insight verification, these capabilities introduce significant arbitrary code execution and system modification risks, making the skill highly vulnerable to prompt injection or misinterpretation, thus classifying it as suspicious due to high-risk behaviors without explicit malicious intent.