LIVE · cybersecurity feed
Live wire
Manic: The Android Malware That Exfiltrates Data Even When the Phone Is OfflineHackers poison arrayref Rust crate to push infostealer malwareNSA, CISA, FBI, DOE, and EPA Warn of Active AI-Assisted Attacks on Siemens S7 PLCsSenators press TikTok over withholding of safety features for some usersAI-Generated Exploit Scripts Target Siemens S7 PLCs in U.S. Critical InfrastructureChatGPT for Teens tackles risky chats and homework shortcutsCritical Elementor Pro bug exposes WordPress sites to RCE attacksNew Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat DataThe push to designate AI as the next critical infrastructure sectorCritical Zimbra RCE flaw now actively exploited in attacks

chatbot vulnerability

ai securityhigh

New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data

Adversa AI has detailed a new attack called Cryptographic Context Injection that can trick xAI's Grok chatbot into sending user data, including name, location, subscription tier, and conversation history, to an attacker-controlled server. The attack exploits the chatbot's Python execution runtime by embedding encrypted instructions that Grok decrypts and executes, leading it to construct a URL containing the sensitive information. While Adversa AI has reported the vulnerability to xAI, there is currently no patch or CVE identifier, and no public statement from xAI regarding mitigation.