Claude Opus 5 Resists Prompt Injection Attacks in Browser Scenarios
KuCoinFlashShare
Anthropic reported that its Claude Opus 5 model demonstrates strong resistance to prompt injection attacks in browser environments, with no security breaches detected across 129 test cases. The model achieved a 2.0% score on Gray Swan’s benchmark, outperforming Opus 4.8 (5.5%), Mythos 5 (2.6%), and Fable 5 (2.8%). Prompt injection remains a significant threat to AI agents; the zero-attack rate was observed only in Claude Cowork with Auto Mode enabled. Interest rate news and market movements are unlikely to impact this security-focused update.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.