可信 — 风险评分 0/100
上次扫描:2 天前 重新扫描
0 /100
mimo-tts
Generate speech audio (WAV) from text using Xiaomi MiMo TTS (mimo-v2-tts model)
MiMo TTS skill is a straightforward text-to-speech wrapper using only Python standard library, making a single authenticated API call to Xiaomi's service and writing audio output — no suspicious patterns.
技能名称mimo-tts
分析耗时18.8s
引擎pi
可以安装
No action needed. The skill is safe to use as described.
资源类型声明权限推断权限状态证据
网络访问 READ READ ✓ 一致 scripts/tts.py:27 urllib.request.urlopen POST to api.xiaomimimo.com
文件系统 NONE WRITE ✓ 一致 scripts/tts.py:93 open(args.output, 'wb') — declared in docs as -o output flag
环境变量 READ READ ✓ 一致 scripts/tts.py:85 os.environ.get('MIMO_API_KEY') — declared in SKILL.md
命令执行 NONE NONE No shell execution found
2 项发现
🔗
中危 外部 URL 外部 URL
https://api.xiaomimimo.com
SKILL.md:13
🔗
中危 外部 URL 外部 URL
https://api.xiaomimimo.com/v1
scripts/tts.py:12

目录结构

2 文件 · 5.5 KB · 167 行
Python 1f · 96L Markdown 1f · 71L
├─ 📁 scripts
│ └─ 🐍 tts.py Python 96L · 3.0 KB
└─ 📝 SKILL.md Markdown 71L · 2.5 KB

安全亮点

✓ Uses only Python standard library (no third-party dependencies)
✓ API key read from environment variable only, not hardcoded
✓ No subprocess, eval, or shell command execution
✓ No access to sensitive paths (~/.ssh, ~/.aws, .env files)
✓ No base64 decode piped to shell
✓ No data exfiltration or credential harvesting beyond the intended API call
✓ Implementation matches documented behavior exactly