LodeHQ
AI news for people who shipFree, by email

Infosec · 0din.ai · Thursday, 9 July 2026

Indirect Prompt Injection Lets Claude Code Hijack Your Machine from a Clean Repo

Researchers Andre Hall and Miller Engelbrecht show how Claude Code can be tricked into opening a reverse shell by chaining a benign README, Makefile and test file, with the actual payload fetched from a DNS TXT record at runtime. The attack demonstrates full system compromise without any malicious code in the repository.

Read the source: 0din.ai ↗In the 9 July issue →