-
Security researchers at Cato CTRL have discovered a new indirect prompt injection technique called HashJack, which weaponises legitimate websites to manipulate AI browser assistants. The attack conceals malicious instructions after the “#” symbol within trusted URLs, enabling threat actors to conduct a wide range of attacks without compromising any website. How HashJack Works The technique exploits […] The post HashJack: New Attack Technique Tricks AI Browsers Using a Simple ‘#’ appeared first on Cyber Security News.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Microsoft is sounding the alarm on critical security considerations as it introduces agentic AI capabilities to Windows through experimental features like Copilot Actions. The company is rolling out a new agent workspace feature in private preview that…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
The Python-based information-stealing tool Xillen Stealer has reached versions 4 and 5, significantly expanding its targeting capabilities and functionality across platforms. Documented initially by Cyfirma in September 2025, this cross-platform infost…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Cybersecurity researchers have identified a sophisticated malware campaign leveraging artificial intelligence to enhance obfuscation techniques, enabling malicious applications to circumvent traditional antivirus detection systems. The threat actors be…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Generative artificial intelligence has fundamentally transformed the landscape of cybercriminal operations by eliminating what was once a critical barrier to entry: the quality of the scam itself. Where scammers previously relied on obvious spelling mi…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Oligo Security researchers have uncovered an active global hacking campaign that leverages artificial intelligence to attack AI infrastructure. The operation, dubbed ShadowRay 2.0, exploits a known yet disputed vulnerability in Ray an open-source frame…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Pig-butchering scams, the sophisticated long-con investment fraud schemes that have plagued millions globally, have reached unprecedented scale through the strategic deployment of artificial intelligence technologies. Once reliant on labor-intensive so…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Security researchers at Oligo Security have uncovered a series of critical Remote Code Execution vulnerabilities affecting widely deployed AI inference servers from major technology companies. The flaws affect frameworks developed by Meta, NVIDIA, Micr…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
SecureVibes, an innovative AI-native security system designed for modern applications, has unveiled a comprehensive vulnerability scanner that leverages Anthropic’s Claude AI to deliver intelligent security analysis across eleven programming lang…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A comprehensive security analysis has uncovered a troubling reality: 65% of leading AI companies have leaked verified secrets on GitHub, exposing critical API keys, authentication tokens, and sensitive credentials that could compromise their entire org…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
