ai-meeting-to-tasks

Warn

Audited by Snyk on Jun 13, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.65). 该技能在运行时会接收用户提供的 materialUrl/materialText/materialFile 作为“会议记录/客户反馈/待整理资料”等可读文本输入(x-required-any-of),其中若 materialUrl 指向公网上任意页面或 materialText 来自他人撰写内容,则会把外部自由文本读入并进入 LLM 上下文,属于“公共网页/他人消息内容”路径的间接提示注入风险。

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 03:31 AM
Issues
1
Security Audit — snyk — ai-meeting-to-tasks