WordlistLoader delivers Amatera via ClearFake ClickFix attacks, while SynkLoader uses Teams phishing to steal Windows login ...

A previously undocumented malware loader, dubbed SynkLoader, that combines Python, C#, and native C++ components to evade ...

A ransomware affiliate weaponized Claude Code to autonomously steal LDAP credentials, backdoor VPNs, and exfiltrate SQL ...

A newly disclosed prompt-injection technique can reportedly turn a routine “summarize this page” request in xAI’s Grok web ...

A newly disclosed attack can turn a routine “summarize this page” request in xAI’s Grok web chat into a silent theft of the ...

Researchers say the new ‘Cryptographic Context Injection’ technique conceals malicious instructions until they are decrypted inside a trusted execution environment.

Five U.S. agencies confirmed August 19 that hackers are using AI-generated scripts to breach internet-exposed Siemens S7 ...

Anthropic published a detailed account on August 14, 2026 of how the text watermark in future Claude models works, identifying it as a version of the SynthID-Text technique Google DeepMind published ...

Researchers found every major AI provider encrypts reasoning tokens with a single global key—and exploited it to decode a trove of data.

A new paper published this week demonstrated that every encrypted reasoning block returned by Anthropic, OpenAI, and Google's AI APIs shares a single global encryption key — meaning any developer who ...