agent-notify@0.1.0
CAUTION· static onlyPublisher claims: "让 agent（Claude Code / Codex / Hermes / OpenClaw 通用）干完活主动播报到语音设备（小智音箱、机器人等）。守护进程读会话记录判断任务状态，完成或卡死时把「任务名+状态+时间」拼成中文播报句推给后台。首次使用需配置后台 WebSocket 地址、设备 MAC、授权码。【服务器端后台设计重点】① 一个 WS 端点即可，握手首帧收 {"mac","code"}，回 {"type":"auth","ok":true} 或 ok:false + error（建议区分 invalid_code 与 session_not_found，客户端会把原文透传给用户）；② 只处理 type=="task_status" 的帧，直接取现成的 text 字段丢 TTS，其余 type 静默忽略——注意静默丢弃在协议层零反馈，排障时极难定位；③ 鉴权铁律：播给哪台设备必须由 code 反查绑定关系，绝不信任请求体里的 mac，否则任何拿到 token 的人改个 MAC 就能往别人设备推送；④ 设备离线是常态而非边界情况（小智类设备约两分钟无人声即断连），后台需要 pending 队列在设备重连后补播并设 TTL，否则大部分通知会蒸发；⑤ 30 秒 ping/pong 保活，客户端断线指数退避重连、握手被拒则不重连；⑥ 播报文案由客户端拼好（状态已译成中文、ISO 时间已转成"下午2点05分"），后台不必二次加工。Triggers 触发词：任务播报, 干完告诉我, 通知机器人, 语音播报, agent-notify, 配置播报, 开启播报, 停止播报, 停止这个skill, 关闭后台监听, 播报状态, 小智播报。" Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-07 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
p = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run([sys.executable, me, *a], env=env,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.srv = subprocess.Popen([sys.executable, srv_py, str(port)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim chujindan-dotcom: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.