PuzzleMask Hides Attacks Inside Plain Prose Text
A small model reads a text and answers “safe.” Then the very same text reaches a more powerful AI, which finds a hidden command within and executes it. Check Point Research has laid bare...
Tagged: AI security
OpenAI Collective Cyberdefense: 128 Firms Warn on AI Attacks
Companies have only a few months left to fortify their defenses before AI markedly accelerates real-world cyberattacks. OpenAI issued that warning in an open letter endorsed by 128 organizations, among them Google, Microsoft, Anthropic,...
AI Agent Finds GitHub Actions Bug, Reaches Snowflake’s Internal Jira
An AI agent designed to hunt for vulnerabilities independently discovered a flaw within a public Snowflake repository and used it to gain access to the company’s internal Jira system. The vulnerability had existed for...
Google ADK Vulnerability Enables Agent to Agent Attacks
The Emergence of Agent-Against-Agent Exploits An AI agent can deceptively trigger another agent with elevated privileges. Consequently, an attacker can exploit this mechanism to compromise a software project. Pillar Security researchers discovered such an...
Acoustic Keystroke Attack Decodes Typing Using Language Models
The acoustic reverberations of keyboard strokes can betray far more information than previously imagined. Recently, a novel side-channel attack demonstrated that a brief audio recording suffices to reconstruct typed text without requiring direct compromise...
AI Sandbox Escape Vulnerabilities Threaten Coding Tools
The Illusion of Isolated Environments As artificial intelligence programming assistants gain unprecedented access to proprietary source code, credential keys, and live execution environments, formal sandbox boundaries no longer guarantee comprehensive endpoint protection. Security researchers...
Malicious npm Worm Targets AI Software Supply Chains
Stealthy Infiltration Tactics A sophisticated new malware conceals itself within standard software development processes. Furthermore, it perfectly mimics legitimate automation tools. Security systems frequently overlook this hidden threat entirely. Meanwhile, the malicious program actively...
AI Connector Risk: They Change Every Nine Minutes
Connecting an AI agent to your working services transforms a familiar integration into something restless. The access chain to your data never stops shifting. ChatGPT and Claude connectors can quietly acquire new capabilities. They...
AI Model Hidden Backdoor Vulnerability
Changing AI behavior is much easier and cheaper than many people thought. Cyber expert Katie Paxton-Fear put a hidden flaw into an open AI model. Amazingly, she finished this task in just about one...
SingGuard-NSFA: Ant Group Open-Sources a Guardrail to Stop Malicious AI Agent Commands After the JadePuffer Attack
Merely twelve days after the first fully automated data-encryption attack came to light, Ant Group has unveiled a free tool designed to halt dangerous artificial intelligence commands before they execute. Developed by Ant Group’s...
Context Bombing: A Novel Defense Against AI Hackers
Malicious commands hidden within text or files have served as tools to breach artificial intelligence systems for years. Now, defenders of these systems have begun utilizing the very same tactic to protect their assets....
The GhostCommit Vulnerability: AI Assistants Weaponized via Images
Invisible Threats in Code Reviews A malicious pull request can bypass code reviews flawlessly. Days later, it compels an AI assistant to covertly exfiltrate project secrets. Attackers simply conceal instructions within an ordinary PNG...
