Claude Sonnet 4.5 Detects Cryptographic Payload Injection
Anthropic's Claude Sonnet 4.5 flagged the payload as prompt injection after decrypting it, showing an ability to detect and mitigate the attack.
Tag: Claude Sonnet 4.5
New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data
Adversa AI has disclosed a novel attack technique dubbed "Cryptographic Context Injection" that can cause xAI's Grok chatbot to exfiltrate a user's…