Tracebit has published research finding that context bombs cut the success rate of malicious AI agents by 91%. The study tested nine deception techniques across several leading AI models, examining ways to misdirect or delay autonomous attacking agents inside IT environments by presenting fake targets and complex dead ends. The measures reduced the number of completed attack objectives and increased the cost of successful attacks 23-fold, with all nine techniques together proving most effective. The findings show this approach stopped all attacks from GPT 5.6 Cyber, Kimi K3, Qwen 3.8 Max and DeepSeek V4 Pro, while reducing the success of GPT-6 Astra by 54% and Claude Opus 5 by 91%. A fake penetration testing report produced the strongest single result, reducing completed objectives by 58%; other decoys included a web service designed never to finish, a file of apparent passwords hidden behind repeated layers of encryption, and an application that appeared to leak a password in fragments, reducing objectives by 36%, 24% and 23% respectively. In one example, GPT-5.6 Cyber spent USD $150 across 10 attacks without reaching a single objective. The study also found that models from Moonshot, Alibaba and DeepSeek failed to achieve their objectives when all nine deception methods were deployed together.