Security audit
Security checks across malware telemetry and agentic risk
This skill is purpose-aligned but should be reviewed because it handles voice cloning, face/avatar media, public media URLs, API tokens, and automated messaging without enough consent and retention safeguards.
Install only if the person whose voice and face are used has explicitly approved cloning, avatar training, hosting, and automated delivery. Use dedicated API keys, verify the LINE recipient IDs, prefer short-lived or access-controlled media URLs, and confirm how ElevenLabs, HeyGen, hosting/CDN, and messaging providers store or delete uploaded and generated media.
**LINE Push API 範例：**
```bash
# 語音
curl -s -X POST https://api.line.me/v2/bot/message/push \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LINE_CHANNEL_ACCESS_TOKEN" \
-d '{- **方法一（官方 UI）**：主人錄 1-3 分鐘語音 → 上傳到 ElevenLabs Voice Lab
- **方法二（主人傳語音給你）**：主人傳語音訊息 → 你下載後用 API 上傳克隆：
```bash
curl -X POST "https://api.elevenlabs.io/v1/voices/add" \
-H "xi-api-key: $ELEVENLABS_API_KEY" \
-F "name=主人的名字" \
-F "files=@/path/to/voice-sample.mp3" \**LINE Push API 範例：**
```bash
# 語音
curl -s -X POST https://api.line.me/v2/bot/message/push \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LINE_CHANNEL_ACCESS_TOKEN" \
-d '{}'
# 影片
curl -s -X POST https://api.line.me/v2/bot/message/push \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LINE_CHANNEL_ACCESS_TOKEN" \
-d '{VirusTotal findings are pending for this skill version.
No suspicious patterns detected.