Security checks across malware telemetry and agentic risk
This voice-chat skill mostly does what it claims, but it needs review because spoken audio can be sent to cloud speech services while parts of the documentation imply local handling.
Install only if you are comfortable granting microphone access and potentially sending speech or transcribed text to Google, ElevenLabs, or other configured providers. Prefer local/offline modes for sensitive conversations, avoid copying the shell=True playback sample, and treat console transcript output as potentially sensitive.
}
}
response = requests.post(url, json=data, headers=headers)
if response.status_code == 200:
with open("output.mp3", "wb") as f:
f.write(response.content)"""使用ElevenLabs TTS"""
import requests
url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}"
headers = {
"xi-api-key": api_key or os.environ.get("ELEVENLABS_API_KEY"),
"Content-Type": "application/json"if result.returncode == 0:
print(f"✅ 语音文件已生成: {output_file}")
# 播放音频
subprocess.run(["start", output_file], shell=True)
else:
print(f"❌ TTS失败: {result.stderr}")
finally:if result.returncode == 0:
print(f"✅ 语音文件已生成: {output_file}")
# 播放音频
subprocess.run(["start", output_file], shell=True)
else:
print(f"❌ TTS失败: {result.stderr}")
finally:66/66 vendors flagged this skill as clean.