Meta's Rogue AI Agent Triggered a Sev 1 Security Breach
An internal Meta AI agent posted to an employee forum without authorization, setting off a two-hour cascade that exposed sensitive internal systems to engineers who lacked clearance.
Articles Tagged "Security"
Best Agent Sandbox Tools in 2026: 10 Options Compared
We compared 10 agent sandboxing tools - from a 99-line shell script to a full Kubernetes cluster. Most agents still run with access to your terminal, files, and AWS keys. Here is how to fix that.
Transformers as Bayes Nets, Memory at Scale, Agent Attacks
Three arXiv papers rethink transformer theory, expose fatal flaws in in-context LLM memory, and introduce grey-box agent security testing.
Linux Foundation Raises $12.5M Against AI Bug Slop
Seven AI and cloud companies pool $12.5M through OpenSSF and Alpha-Omega to build tools that help open-source maintainers cope with a flood of AI-generated vulnerability reports they can't triage.
NVIDIA Open-Sources the Sandbox AI Agents Should Have Had
NVIDIA released OpenShell at GTC 2026 - an open-source runtime that sandboxes AI agents with locked filesystems, blocked networks, and YAML-defined policies. One command to secure Claude Code, Codex, or OpenClaw.
North Korea Targets Europe with AI Deepfake Workers
DPRK operatives use real-time deepfake video and LLM-generated CVs to pass European hiring pipelines, funneling income back to Pyongyang's weapons programs.
China's Top Cybersecurity Firm Ships SSL Key in AI App
Qihoo 360 shipped its AI assistant 'Security Claw' with the wildcard SSL private key for *.myclaw.360.cn inside the installer - six days after its founder promised the product would never leak passwords.
Hundreds of LLM-Written GitHub Repos Are Malware
We ran the GitHub search query from a researcher's blog post and confirmed 300+ malicious repositories with AI-generated READMEs distributing info-stealers - with the real number likely north of 1,000.
Microsoft Patches 84 Flaws - AI Found the Worst One
Microsoft's March 2026 Patch Tuesday fixes 84 vulnerabilities including a CVSS 9.8 RCE discovered by XBOW's autonomous AI agent, an Azure MCP Server SSRF, and an Excel XSS that hijacks Copilot to exfiltrate data.
JBDistill Generates Its Own Jailbreaks - 81.8% Attack Rate
Johns Hopkins and Microsoft's JBDistill achieves 81.8% attack success rate across 13 LLMs by auto-generating fresh adversarial prompts on demand.
China Restricts OpenClaw AI in Government and Banks
Chinese authorities ordered government agencies and state-owned banks to remove or restrict OpenClaw, citing security risks from the AI agent's autonomous operation and broad data access.
Anthropic's Claude Found 22 Firefox CVEs in 14 Days
Claude Opus 4.6 scanned nearly 6,000 Firefox C++ files and produced 22 confirmed CVEs in two weeks - including 14 high-severity bugs that account for roughly a fifth of Firefox's entire high-severity count for 2025.
