Anthropic’s Opus 5 reportedly cuts browser prompt injection success to zero in 129 tests
The Decoder · rss · 2026-07-25
A The Decoder article reports that Anthropic's Opus 5 may have solved browser-based prompt injection, one of the most persistent security issues for AI agents.
- In 129 test scenarios, Opus 5 combined with Auto Mode achieved a 0% prompt injection success rate for browser agents.
- Without those additional protection layers, the success rate was 3.7%.
- If the result holds up in practice, it would be a major step toward safer browser-operating agents.
More from Models
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27
- Open Models Match GPT-6 on MedMCQA but Trail 17 Points on Hard Clinical Cases — keunwoochoi · 2026-10-27
- Health-Focused Benchmark Reranks LLMs: Muse Spark Open Jumps from #9 to #1 — keunwoochoi · 2026-10-27