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
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11