Breaking Claude Code Opus 5 Auto Mode

Embrace The RedAugust 27, 2026AI

In this post, we explore how a simple website summary request hijacks Claude Code Opus 5 in Auto Mode and achieves code execution with 60-80% attack success rate using a small sample size. This is interesting because a third-party evaluation commissioned by Anthropic showed a 0.00% prompt injection attack success rate for Opus 5 in Auto Mode.

Summary from Embrace The Red.

Read the full article at Embrace The Red

Explained

The technology and terms in this story. Learn more

AttackPrompt injectionHiding instructions in content an AI reads, so it follows the attacker instead of its user.

Breaking Claude Code Opus 5 Auto Mode

Explained

More in AI

GPT-6.1 Terra meets OpenAI’s Critical cyber threshold, and it’s cheaper than GPT-5.6 Terra

So Many AI Security Benchmarks, But None Tell the Whole Story

Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang

Risks & Rewards: How AI Is Redefining the CISO's Role

Alibaba's Qwen AI caught trying to contact server in China