wjs-voicedrop-reading-aloud
Warn
Audited by Snyk on Aug 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). 工作流会从用户提供的“URL(WebFetch/browse 渲染)”或“VoiceDrop 文章(voicedrop MCP 的 read_article)”读取正文并在第2-3步将其重写成朗读脚本后喂给 tts.py/seed-tts(间接注入文本可先被 LLM 消费)。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata