**Snyk Finds Prompt Injection in 36% of Payloads in a ToxicSkills Study** > Sny

**Snyk Finds Prompt Injection in 36% of Payloads in a ToxicSkills Study**

> Snyk’s ToxicSkills research reveals 36% of AI agent skills contain security flaws, including 1,467 vulnerable skills and active malicious payloads targeting OpenClaw, Claude Code, and Cursor users. Snyk Finds Prompt Injection in 36%, 1467 Malicious Payloads in a ToxicSkills Study of Agent Skills Supply Chain Compromise Written by Luca Beurer-Kellner Aleksei Kudrinskii Marco Milanta Kristian Bonde Nielsen Hemang Sarka...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-06-26 04:09（北京时间）
- **原文**：[打开原文](https://snyk.io/blog/toxicskills-malicious-ai-agent-skills-clawhub)