AIFIRST Breaking Claude Code Opus 5 Auto Mode
The brief
Security researcher Johann Rehberger demonstrated a reliable prompt injection attack against Claude Code's Auto Mode achieving 60-80% code execution success rates via Python module shadowing.
Key points
- The attack exploits the model's tendency to write and run its own decoder for obfuscated archives, allowing malicious code in a shadowed struct.py to execute on import.
- The findings directly contradict Anthropic's published claim of 0% prompt injection vulnerability in Auto Mode.
Sources
- HNembracethered.com