by 安全扫描
OpenClaw
安全
high confidence该技能的代码、指令和环境变量与AssemblyAI转录集成一致，包中没有意图误导或隐藏数据泄露的迹象。
评估建议
该技能如其所述：上传音频到AssemblyAI并返回带speaker标签的转录文本。安装前注意：(1) 音频发送到第三方服务（AssemblyAI），仅用于非敏感音频；(2) 安全存储API密钥（环境变量或配置文件）；(3) 代码中未实现README提到的Telegram支持（可能为文档不匹配）；(4) 整个文件加载到内存后上传，避免大文件。若需明确保证，请要求作者确认配置路径行为和AssemblyAI账户的隐私/数据保留声明。...详细分析 ▾
✓ 用途与能力
Name/description ask for AssemblyAI transcription with diarization and the code calls AssemblyAI's /upload and /transcript endpoints and requires ASSEMBLYAI_API_KEY — this is coherent. One minor mismatch: README mentions 'Telegram Support' but no Telegram code is present.
ℹ 指令范围
SKILL.md instructs use of an API key and running the provided script, which stays within the stated purpose. The script does check for a config file in multiple locations (home, cwd) which is expected, but also checks Path(__file__).parent.parent.parent.parent / '.assemblyai_config.json' (a high-level ancestor path that can resolve to the filesystem root on typical layouts) — odd but not clearly malicious. The script uploads audio (local or by URL) to AssemblyAI as expected; it does not attempt to read other unrelated files or system secrets.
✓ 安装机制
No install spec included (instruction-only with a small Python script). Nothing is downloaded or written to disk at install time by the skill bundle itself.
ℹ 凭证需求
Only ASSEMBLYAI_API_KEY is required, which is proportionate. The code also supports reading a config file from several locations (home, cwd, and an unusual high-level ancestor path); users should be aware where they place their API key so it isn't read from an unexpected location.
✓ 持久化与权限
Skill is not always-enabled and does not request elevated or persistent platform privileges. It does not modify other skills or system-wide settings.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.1.02026/2/8
添加英文文档和包含必需环境变量的元数据
● 可疑
安装命令
点击复制官方npx clawhub@latest install assemblyai-transcriber
镜像加速npx clawhub@latest install assemblyai-transcriber --registry https://cn.longxiaskill.com
技能文档
AssemblyAI 转录工具 🎙️
转录音频文件，支持speaker diarization（谁在什么时候说话）。功能
- ✅ 支持100+语言转录
- ✅ 支持speaker diarization（Speaker A, B, C...）
- ✅ 每个语句的时间戳
- ✅ 自动语言检测
- ✅ 支持MP3, WAV, M4A, FLAC, OGG, WEBM格式
安装
- 创建AssemblyAI账户：https://www.assemblyai.com/
- 获取API密钥（免费套餐：每月100分钟）
- 设置环境变量：
export ASSEMBLYAI_API_KEY="your-api-key"
// ~/.assemblyai_config.json
{ "api_key": "YOUR_API_KEY" }
使用
本地音频转录
python3 scripts/transcribe.py /path/to/recording.mp3
从URL转录
python3 scripts/transcribe.py https://example.com/meeting.mp3
选项
python3 scripts/transcribe.py audio.mp3 --no-diarization # 跳过speaker标签
python3 scripts/transcribe.py audio.mp3 --json # 原始JSON输出
输出格式
## 转录文本
语言: EN
时长: 05:32
Speaker A [00:00]: 欢迎会议...
Speaker B [00:03]: 谢谢，高兴见到大家...
定价
- 免费套餐: 每月100分钟免费
- 之后: 大约每分钟$0.01
提示
- 为了最佳的speaker diarization：清晰的speaker切换，尽量减少重叠
- 背景噪音过滤良好
- 多语言自动检测可靠
作者: xenofex7 | 版本: 1.1.0