Unverified50% confidenceFactExact time
攻击链利用初始化脚本查询DNS的TXT记录，将恶意shell命令藏在TXT字段中，脚本执行DNS查询时返回的文本被直接传入执行函数完成注入
1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
The Security Risks of Running Unfamiliar Repos with Claude Code: How AI Agents Get Hijacked
bilibiliAIlazy俊7/7/2026
Related Claims
Unverified攻击者可利用npm的postinstall脚本机制在包安装时自动执行任意代码58% similarUnverified规则文件本质上是一种系统提示词注入机制，工具启动时会自动将文件内容作为系统级提示词注入到每次对话上下文中57% similarPartially VerifiedPrompt injection is divided into two categories—direct injection and indirect injection—where indirect injection refers to attackers concealing malicious instructions in external content that the AI may read, such as webpage body text, code comments, README files, and image OCR text.57% similarUnverified工具调用机制使LLM突破纯文本输出边界，直接操纵代码解释器、数据库接口、文件系统及外部API57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/391518API
curl https://kongchang.com/api/v1/knowledge/claims/391518MCP
get_claim(id=391518)