← 返回 Skills 市场
terry-camsnap
作者
terrycarter1985
· GitHub ↗
· v1.0.0
· MIT-0
30
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install terry-camsnap
功能描述
Take camera snapshots and save them to disk. Use when the user asks to take a photo, capture an image from webcam, or take a snapshot.
使用说明 (SKILL.md)
Take a snapshot from the default webcam using the camsnap utility.
Usage
/camsnap [output_path] [--preview] [--output-dir DIR]
If no output path is provided, the snapshot will be saved to the ./snapshots/ directory with a timestamp filename.
Steps
- Run the snapshot script:
python3 ~/.openclaw/workspace/src/camsnap.py {{ $ARGUMENTS }}
- Confirm the snapshot was saved successfully and return the file path.
Notes
- The script discards the first few warm-up frames to avoid underexposed captures.
- Output paths are validated against path-traversal; only allowed directories are writable.
- Use
--previewonly in environments with a display (headless servers will fail).
安全使用建议
Install only if you can inspect or trust the missing camsnap.py helper. Use it only for explicit photo requests, confirm where images will be saved, and remember that webcam snapshots may capture sensitive surroundings.
功能分析
Type: OpenClaw Skill
Name: terry-camsnap
Version: 1.0.0
The skill is classified as suspicious due to a shell injection vulnerability in SKILL.md, where user-provided arguments are passed directly into a Bash command string (python3 ... {{ $ARGUMENTS }}). While the stated purpose of taking webcam snapshots is legitimate, the lack of argument sanitization allows for potential command execution. Additionally, the skill interacts with sensitive hardware (webcam) and references an external script (camsnap.py) not provided in the bundle.
能力评估
Purpose & Capability
Taking a webcam snapshot and saving it to disk matches the stated purpose, but camera capture and saved image files are privacy-sensitive.
Instruction Scope
The instructions grant Bash access and pass user-supplied arguments directly into a shell command, so the actual command scope depends on unsafe interpolation and an unreviewed helper script.
Install Mechanism
There is no install spec and no provided code, yet the skill depends on ~/.openclaw/workspace/src/camsnap.py, creating a provenance and review gap.
Credentials
The skill does not request credentials or network access, but it implicitly needs Python, webcam access, and possibly display support, none of which are declared as requirements.
Persistence & Privilege
No background persistence or credential use is shown, but captured photos are intentionally written to disk and may contain sensitive visual information.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install terry-camsnap - 安装完成后，直接呼叫该 Skill 的名称或使用
/terry-camsnap触发 - 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
v1.0.0
v1.0.0: Fix code-review findings — add path-traversal guard, warm-up frames for exposure, resource-leak protection (finally), imwrite return check, logging instead of print, type annotations; rename skill.md to SKILL.md per ClawHub spec; update skill docs.
元数据
常见问题
terry-camsnap 是什么？
Take camera snapshots and save them to disk. Use when the user asks to take a photo, capture an image from webcam, or take a snapshot. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 30 次。
如何安装 terry-camsnap？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install terry-camsnap」即可一键安装，无需额外配置。
terry-camsnap 是免费的吗？
是的，terry-camsnap 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
terry-camsnap 支持哪些平台？
terry-camsnap 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 terry-camsnap？
由 terrycarter1985（@terrycarter1985）开发并维护，当前版本 v1.0.0。
推荐 Skills