Tag
Anthropic's Claude Opus 4.6 discovered 14 high-severity bugs in Firefox including a CVSS 9.8 JIT flaw, demonstrating that AI security research can find logic errors traditional tools overlook.
A prompt injection attack against Cline's AI triage bot escalated into a supply chain compromise - installing unauthorized software on thousands of developer systems.
CVE-2026-2256 in ModelScope's MS-Agent framework enables command injection through prompt manipulation, with no vendor patch available.
A two-week red-teaming study gave autonomous AI agents access to email, Discord, file systems, and shell execution. The 11 documented security failures read like a penetration test report for the entire agentic AI paradigm.
88% of organizations report AI agent security incidents. Only 14% deploy agents with full security approval. When autonomous systems cause harm, traditional accountability breaks down.
Most companies have no idea what their AI systems are actually doing. A CrowdStrike-backed startup thinks it can change that.
Zenity Labs reveals how a malicious calendar event could let attackers hijack Perplexity's Comet browser to exfiltrate local files and take over your 1Password account.
Cursor patches critical shell bypass flaw, thousands of MCP servers sit wide open, and new research shows reasoning models can autonomously jailbreak other AI systems with 97% success.
A patched Chrome vulnerability let malicious extensions hijack Gemini's access to your camera, microphone, and files. Here's what happened.
Veea releases a sub-millisecond security proxy for AI agents under MIT license as new research shows 88% of organizations have experienced agent security incidents.
Google and Cloudflare are deploying Merkle Tree Certificates to protect HTTPS against quantum computer attacks without breaking the internet
A veteran Google security engineer built a sandbox system that treats AI agents as fundamentally untrusted - and it could be the model for safe agent deployment.
A perfect 10.0 CVSS vulnerability in the popular workflow automation platform lets attackers hijack self-hosted instances used for AI agent automation without authentication.
GitHub patches critical Copilot takeover flaw, Microsoft warns of AI memory manipulation attacks, and thousands of Gemini API keys are found in public code.
Former Google and Stripe security head Niels Provos built an open source sandbox that assumes AI agents will go rogue. Here's how it works.
Cisco's 2026 State of AI Security report reveals a dangerous gap: enterprises are deploying AI agents faster than they can secure them, with MCP vulnerabilities and prompt injection attacks proliferating.
Security researchers found that simply opening an untrusted repository in Claude Code could execute arbitrary commands and steal your Anthropic API keys - all before you saw a warning.
IBM's annual threat intelligence report reveals attackers are using AI to accelerate vulnerability discovery while infostealer malware harvests hundreds of thousands of AI chatbot credentials from the dark web.
New paper shows 'intent laundering' bypasses Gemini, Claude, and other models with 90-98% success by removing obvious attack cues
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.
Anthropic's flagship model bypassed by security researchers who extracted detailed sarin gas and smallpox synthesis instructions
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.
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.
