Opus 5 combined with Auto Mode hits a zero percent prompt injection success rate for browser agents across 129 test scenarios. Without those extra protection layers, the rate is 3.7 percent. If these numbers hold up in practice, Anthropic may have cracked one of the biggest security problems facing AI agents that operate in browsers.
The article Opus 5 may have solved browser-based prompt injection, the biggest security flaw haunting AI agents appeared first on The Decoder.
source & further reading
the-decoder.com — original article
Anthropic's Claude Opus 5 costs well below Fable 5 while matching or beating it across most benchmarks
Microsoft's open-weight AI push is so obviously an Azure play it hurts
Sakana claims its AI model router Fugu Ultra v1.1 now beats Fable 5 without even including it in the pool