Tag: ai security
177 articles
Security Researchers Exploit 47 Zero-Days for $1.3 Million at Pwn2Own Berlin
In a stunning display of cybersecurity prowess, researchers at Pwn2Own Berlin 2026 exploited a whopping 47 zero-day flaws, raking in a total of $1.3 million in just three days. The competition saw contestants disclose and exploit vulnerabilities in top enterprise and AI-facing products, earning daily payouts of $523,000, $385,750, and $389,500.
SecurityScorecard Bolsters Internet Visibility with Driftnet Acquisition
SecurityScorecard has acquired Driftnet, an internet scanning startup, to supercharge its third-party risk management capabilities with deeper, real-time visibility into internet infrastructure and hidden exposures. This strategic move allows SecurityScorecard to directly control data quality and drive future innovation in AI security.
Securing Autonomous AI Requires New Risk Strategies
Autonomous AI agents are revolutionizing enterprise environments with lightning-fast speed, unprecedented autonomy, and access to sensitive systems and data - but many security teams lack the visibility and control to manage the resulting risks. This game-changing technology is rapidly expanding the enterprise attack surface, demanding new risk strategies to stay ahead.
TeamPCP hackers target Mistral AI code repos for sale
Hackers from TeamPCP are demanding $25,000 for nearly 5 gigabytes of stolen Mistral AI code, threatening to leak it for free if they don't find a buyer within a week. The group claims to have snagged around 450 internal repositories, including sensitive source code used for training and model delivery.
OpenAI's GPT-5.5 Matches Mythos in Security Vulnerability Detection
The UK's AI Security Institute just put GPT-5.5 to the test, and the results are impressive: it can detect security vulnerabilities on par with the highly-regarded Claude Mythos. This achievement is especially significant since GPT-5.5 is widely available for use.
Claude Code Attack Persists Through Token Rotation Flaw
A surprising lack of resistance to a proof-of-concept attack has exposed a vulnerability in Claude Code, allowing a five-step attack chain that can turn routine token rotation into a continuous compromise. This exploit requires just one malicious npm package and the ability to run code on a developer's machine, making it a concerning threat.
G7 Guidance Sets AI Security Standards
The G7 has set a new benchmark for AI security with the release of voluntary guidelines, outlining the minimum requirements for transparency around AI system components. This move aims to establish a common baseline for the industry, promoting trust and safety in the rapidly evolving AI landscape.
Security Teams Lag Behind on Agentic AI Risks
The alarming truth is that agentic AI is already live in many production environments, but security teams are largely in the dark about the risks they're facing. This emerging threat can be categorized into three key areas: coding and productivity agents like Claude Code and GitHub Copilot, vendor-built agents, and custom-built agents.
Hugging Face Repository Exploits Typosquatting to Spread Infostealer Malware
Security researchers have uncovered a cunning malware attack on Hugging Face, where a fake repository mimicked a popular AI project, racking up over 244,000 downloads and 667 likes in just 18 hours. The malicious repository used a classic typosquatting trick to deceive users searching for the genuine project.
Mini Shai-Hulud Worm Targets Multiple AI, Dev Packages
Meet the Mini Shai-Hulud worm, a sneaky new malware that's infiltrating AI and development packages through a clever supply-chain attack. This malicious code can steal sensitive data from cloud providers, cryptocurrency wallets, and even popular dev tools like GitHub Actions.
Steganography Exploits LLMs with Hidden Text Techniques
Want to hide text in plain sight? Try using white text on a white background or black text on a black background - simple yet effective visual tricks that can evade human eyes while remaining readable by machines.
Anthropic's AI Tool Exposes to One-Click Remote Code Execution Risk
A single click on Claude Code's generic dialog can unleash a major security risk, allowing an unsandboxed Node.js process to spawn with full user privileges. This vulnerability can be exploited using just two common JSON files, putting developers at risk of one-click remote code execution.
Legacy Security Tools Hinder Data Protection Efforts
With data constantly moving across cloud and AI environments, traditional security tools are holding you back from truly protecting your data - it's time for a modern approach. A staggering 72% of security professionals agree that data security is more critical than ever, making an evolution in strategy urgent.
AI Exploits Emerge as New Security Threat
As AI use grows, a hidden risk is emerging: malicious inputs can alter model behavior, bypassing safeguards and putting enterprises at risk. This "prompt injection" tactic is like phishing, targeting the link between user and system to wreak havoc.
AI-BOMs Emerge to Secure Enterprise AI Supply Chains
Imagine biting into a mysterious birthday cake without knowing its ingredients or who baked it - that's what it's like for enterprises trying to secure their AI supply chains without visibility into the components used to build their AI systems. Traditional software bills of materials just aren't cutting it in this new landscape.
ServiceNow Unveils AI Command Center to Tame Enterprise AI Assets
ServiceNow's AI Command Center brings order to enterprise AI assets, ensuring every system is secure, compliant, and aligned with your business strategy. This powerful tool tackles AI agent sprawl by offering a unified control tower across five key areas: discovery, observation, governance, security, and measurement.
NHS Moves to Close-Source GitHub Repos Citing AI Security Risks
The NHS is taking steps to boost security by moving its public GitHub repositories to private access by May 11, amid concerns that AI-powered code analysis could be exploited to uncover sensitive information. This temporary measure aims to prevent unintended disclosure of source code and other critical details.
Palo Alto Networks Bolsters AI Security With Portkey Acquisition
Palo Alto Networks is taking a major leap in AI security with its acquisition of Portkey, a cutting-edge startup that offers an AI agent gateway to streamline and secure communications among autonomous agents. This move will enable centralized control and oversight, ensuring safer interactions between AI agents.
Open Source Models Challenge Dominance in Automated Bug Finding
The impressive performance of Anthropic's Mythos in automated bug finding, which uncovered 271 Firefox flaws, has been called into question by Ari Herbert-Voss, who argues that open-source models can be just as effective. Herbert-Voss suggests that Mythos's success can be attributed to its ability to detect both simple and complex vulnerabilities, thanks to a phenomenon he terms "supralinear scaling".
Frontier AI Exposes Gaps in Traditional Security Programs
Imagine having the power to replicate a full year’s worth of manual penetration testing in just three weeks - that's the reality with frontier AI, which has exposed significant gaps in traditional security programs. Palo Alto Networks and Unit 42 have revealed that advanced models like Anthropic Mythos can autonomously identify software vulnerabilities and adapt to defensive controls in near-real-time.
Anthropic's Claude Mythos Exposes AI Vulnerability Risks
The recent exposure of Anthropic's Claude Mythos highlights a chilling reality: AI tools designed to improve software quality can be easily repurposed to accelerate vulnerability discovery for malicious ends. This underscores the growing threat of AI-powered attacks, as malicious actors exploit commercial tools with minimal friction.
Researchers Expose AI Agents to Malicious Prompt Injection Payloads
Imagine a browser AI that can summarize web pages, but with a hidden vulnerability that allows malicious instructions to be embedded and executed - a newly discovered threat that security researchers are warning deserves our attention. Forcepoint researchers have uncovered 10 real-world examples of indirect prompt injection payloads designed to subvert AI agents and wreak havoc.
Anthropic's Mythos Model Exposes Limited Capabilities
Anthropic's highly anticipated Mythos model, designed to proactively identify vulnerabilities, has been compromised - with a small group of individuals reportedly gaining unauthorized access to the preview through a third-party vendor environment. The incident has raised concerns about the model's limited capabilities to protect itself from exploitation.
Google's Antigravity AI Flaw Exposes Remote Code Risk
Google's top-of-the-line Antigravity AI safeguard can be surprisingly easily tricked into letting its guard down, leaving the door open for attackers to execute remote code. Even with its highest security setting, the AI agent manager's weaknesses can be exploited, putting users at risk.