Tag
Android malware using Gemini for real-time evasion. A low-skill attacker using Claude and DeepSeek to compromise 600 networks. NIST launches an emergency standards initiative. Welcome to February 2026.
Amazon threat researchers tracked a Russian-speaking attacker who used commercial AI tools to compensate for limited hacking skills. The result: 600+ FortiGate devices compromised across 55 countries.
Anthropic's flagship model bypassed by security researchers who extracted detailed sarin gas and smallpox synthesis instructions
A bug allowed Microsoft 365 Copilot to summarize emails marked with confidentiality labels, bypassing DLP protections. Microsoft says no one saw data they weren't authorized to see. That misses the point.
This week in AI security: Chat & Ask AI exposes 300 million messages, Microsoft patches Copilot email vulnerability, and vibe-coded apps prove trivially hackable.
Kaspersky research reveals that passwords from ChatGPT, DeepSeek, and Llama lack true randomness. The same prediction capability that makes LLMs useful makes them terrible at generating secure passwords.
Microsoft Semantic Kernel has back-to-back CVSS 10.0 vulnerabilities enabling remote code execution and arbitrary file writes through AI agent function calls
A CVSS 9.8 flaw in the popular AI inference engine allows unauthenticated remote code execution through malicious video URLs. Patch now if you're running multimodal models.
A new report finds most enterprises deploying AI agents have already experienced security breaches, but executives remain overconfident.
Microsoft found 31 companies embedding hidden instructions in AI share buttons. One click poisons your assistant's memory, shaping every future recommendation without your knowledge.
Two vulnerabilities in the popular Chainlit AI framework allow attackers to steal cloud credentials, API keys, and user data from enterprise chatbots.
Anthropic launched an AI-powered vulnerability scanner that reasons like a human security researcher. CrowdStrike, Okta, and Cloudflare dropped 8% on the news.
Researchers discovered that displaying an AI model's reasoning process creates a roadmap for attackers. OpenAI's o1 rejection rate dropped from 98% to under 2%.
ESET discovers Android malware that queries Google's Gemini AI in real-time to navigate infected devices and maintain persistence across any Android version.
A Cybernews analysis of 1.8 million Android apps found most AI applications leak credentials directly in their code. Over 200 million files were exposed through misconfigured databases.
Check Point demonstrated how AI assistants with web browsing can relay malware commands through legitimate AI traffic. Microsoft patched Copilot; xAI hasn't commented on Grok.
Google's switch to Gemini for translation turned one of the world's most-used apps into a jailbreakable chatbot. Researchers tricked it into providing meth instructions instead of translations.
The largest global collaboration on AI safety just published its findings. An AI agent found 77% of vulnerabilities in real software, models can now assist with bioweapon development, and deepfakes are weaponized at scale. Here's what 100 experts want you to know.
New research proves AI models will refuse harmful requests verbally while executing them through tool calls
The viral AI agent went from 135K GitHub stars to enterprise blacklists in three weeks. Here's what went wrong and why it matters for every AI agent.
New research shows AI reasoning models can autonomously plan and execute attacks that bypass safety guardrails in nearly all other AI systems.
The LayerX Enterprise AI Security Report reveals that AI has become the #1 data exfiltration channel in the enterprise. 82% of those leaking data use personal accounts. Traditional DLP can't stop copy-paste.
Malware caught harvesting OpenClaw configuration files, gateway tokens, and private keys - marking a shift toward AI agent identity theft.
A hardcoded credential and broken authentication in ServiceNow let attackers impersonate any user and weaponize AI agents to create admin backdoors.