voice-clone
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). 该 Skill 在运行时会把用户提供的
--text或--text-file内容作为 JSON payload 发送到远端 Gradio(post_json(..., {"data": [read_text(args), ...]})),因此若文本来自外部/非操作用户(如他人消息或下载文件),其自由文本会进入 LLM 上下文;脚本本身不做净化/来源校验。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata