← 返回 Skills 市场
lubingshun

SmartEye - Agent的眼睛

作者 lubingshun · GitHub ↗ · v3.0.0 · MIT-0
cross-platform ✓ 安全检测通过
199
总下载
2
收藏
0
当前安装
14
版本数
在 OpenClaw 中安装
/install smart-eye
功能描述
Control and analyze ONVIF PTZ IP cameras to capture frames, view streams, find objects, and perform pan-tilt-zoom movements using configured camera aliases.
安全使用建议
This skill appears to do exactly what it says: control ONVIF PTZ cameras and capture frames. Before installing, consider: 1) camera credentials are stored in camera-devices.json in your workspace—replace example passwords and protect that file (file permissions, do not expose it to others); 2) ONVIF/RTSP traffic is usually plaintext—use only on a trusted internal network and do not expose cameras to the public Internet; 3) snapshots are saved locally and the skill instructs the agent to use an image tool to analyze them—if your agent's image tool sends images to external services, those captured frames could be transmitted off-host; 4) the code disables SSL verification in places for convenience (common in device tooling) — this reduces transport authenticity but is typical for local device control; 5) SKILL.md describes an "instruction-only" skill but the package includes code and a dependency on opencv-python; ensure your environment can satisfy opencv and you are comfortable running the packaged code. If you need stronger guarantees, review/inspect the included Python files locally (they are bundled with the skill) and ensure camera-devices.json uses correct internal IPs and secure passwords.
功能分析
Type: OpenClaw Skill Name: smart-eye Version: 3.0.0 SmartEye is a legitimate camera management skill for OpenClaw that enables PTZ (Pan-Tilt-Zoom) control and snapshot analysis for TP-Link and Huawei devices. It utilizes standard protocols like ONVIF (via SOAP) and RTSP (via OpenCV) to interact with local network cameras. While the skill stores camera credentials in plain text within 'camera-devices.json' and disables SSL verification for local compatibility, these are common vulnerabilities in IoT integrations rather than evidence of malicious intent. No indicators of data exfiltration, unauthorized remote execution, or prompt injection attacks were found.
能力评估
Purpose & Capability
Name/description match the implementation: code implements ONVIF/PTZ control, RTSP snapshot capture (opencv), VLC launching, and multi-camera snapshot search. No unrelated environment variables, external cloud credentials, or surprising binaries are requested; camera credentials are provided via the local camera-devices.json config as expected for this purpose.
Instruction Scope
SKILL.md describes the same behaviors the code implements: copying a bundled template to ~/.openclaw/workspace/camera-devices.json, reading camera credentials from that file, taking snapshots, opening RTSP in VLC, and producing snapshot paths for AI/image analysis. The runtime instructions and code do not read unrelated system files or hidden endpoints. They do perform network requests to the camera hosts specified in the config (expected for camera control).
Install Mechanism
No install spec is present (the package relies on included code and a pyproject listing opencv-python). This is consistent with a local skill bundle, but the SKILL.md earlier said "instruction-only" while the package includes code—this is an informational mismatch (not necessarily malicious). There are no download-from-URL installs or obscure external installers.
Credentials
The skill requests no environment variables or external credentials. It does require plaintext camera credentials stored in camera-devices.json (username/password per camera) which is proportional and expected for direct device control. The README warns about replacing example passwords and keeping the file on an internal network. No unrelated secrets are requested or embedded.
Persistence & Privilege
always:false and the skill does not request system-wide privileges. It copies a bundled template into the user's workspace path (~/.openclaw/workspace) on first run (documented), which is reasonable. The skill does not modify other skills' configs or enable itself globally.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install smart-eye
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /smart-eye 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.0.1
更新描述措辞,优化核心能力表格说明,触发词示例更贴近实际用法
v3.0.0
重建 v3.0.0 - 全新发布,完整功能:PTZ云台控制/抽帧截图/多摄找东西/VLC调阅/别名定位/配置表格优化
v2.3.0
安全修复: 移除所有sys.path外部依赖hack/清空模板真实IP/修复huawei_ptz.py重复docstring/重新基于完整功能版上传
v1.2.0
安全修复: 移除workspace外部依赖/tplink.py不再从用户workspace动态import代码/所有凭证从camera-devices.json读取而非硬编码
v1.1.0
重写介绍/加别名支持/修复配置表格/移除已知问题/清除真实密码
v2.2.0
v2.2.0 新增找东西功能: 帮我找钥匙/钥匙在哪里/有没有猫,自动并行截图所有已接入摄像头并引导AI分析目标所在位置;修复pyproject.toml缺失opencv-python依赖;搜索词自动去除我的/那只/一个等前缀
v2.1.0
v2.1.0 自然触发词: 看看/分析/分析一下/画面均触发截图并返回路径;SKILL.md大幅更新,区分看看(截图AI分析)和调阅(VLC取流)的使用场景
v2.0.0
v2.0.0 新增看的能力: 1) RTSP抽帧截图(tplink截图/华为截图) 2) VLC实时流调阅(tplink调阅) 3) 截图保存到Skill目录snapshots/ 4) 新增rtsp_port/rtsp_path/vlc_path配置字段 5) SKILL.md全面更新,增加配置字段说明和触发词表格
v1.0.5
v1.0.5 修正文档: 删除SKILL.md中已过时的可信目录警告(代码已不再从workspace/camera导入模块,文档与实际一致)
v1.0.4
v1.0.4 最终清理: 移除所有workspace/camera依赖,删除legacy fallback函数,彻底消除sys.path插入用户可写目录
v1.0.3
v1.0.3 修复硬编码凭证: 重构onvif_ptz_control.py为TPClient类,凭证从camera-devices.json动态读取,彻底移除硬编码HOST/PASS/PTZ_TOKEN
v1.0.2
v1.0.2 彻底修复: 将 onvif_ptz_control.py 打包进 Skill,TP-Link/Huawei 均不再依赖 ~/.openclaw/workspace/camera/ 外部模块
v1.0.1
v1.0.1 安全修复: 移除捆绑模板明文密码,修夏SKILL.md与代码路径不一致,补充SSL/凭证安全说明
v1.0.0
v1.0.0: TP-Link + 华为摄像头 PTZ 控制,支持点头/摇头/上下左右转/放大/缩小/居中/停止/状态
元数据
Slug smart-eye
版本 3.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 14
常见问题

SmartEye - Agent的眼睛 是什么?

Control and analyze ONVIF PTZ IP cameras to capture frames, view streams, find objects, and perform pan-tilt-zoom movements using configured camera aliases. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 199 次。

如何安装 SmartEye - Agent的眼睛?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install smart-eye」即可一键安装,无需额外配置。

SmartEye - Agent的眼睛 是免费的吗?

是的,SmartEye - Agent的眼睛 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

SmartEye - Agent的眼睛 支持哪些平台?

SmartEye - Agent的眼睛 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 SmartEye - Agent的眼睛?

由 lubingshun(@lubingshun)开发并维护,当前版本 v3.0.0。

💬 留言讨论