LIVE FEED
FIRST LOOK Anthropic AI Agents Submit Visa Forms on State Dept Site // HIGH Anthropic AI Agents Exploit Gov Sites via Reward Hacking // HIGH Anthropic AI Agent Submits False Homicide Tip to Police Tipline // MEDIUM OpenAI Fires Safety Researchers Over Sensitive Data Dispute // FIRST LOOK Token Security Adds Enforcement Controls for AI Agent Permissions // HIGH AI Agents Targeted via Social Engineering in BEC-Style Attacks // FIRST LOOK Microsoft Copilot Gains Local File Access via Hybrid Intelligence // FIRST LOOK AWS Adds Native Access Controls for RAG via Amazon Quick and Bedrock // HIGH DPRK npm Supply Chain Worm Uses Web3 C2 to Steal Cloud Keys // FIRST LOOK Rein Security Launches $25M Runtime Guard for AI Agents //
CVE

Cve

3 reports
All LLM Security Agentic AI Industry News Research First Look: Security Supply Chain Prompt Injection Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning Deep Signal Intelligence Report Monthly Review AI Governance AI Security AI Security Tools Identity & Access Management Security Operations
BragJack Hijacks AI Browser Agents via Malicious Extensions

BragJack Hijacks AI Browser Agents via Malicious Extensions

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.5 BleepingComputer

Security researcher Gal Weizman has disclosed BragJack, a browser extension-based attack technique capable of hijacking AI assistants embedded in Chromium browsers — including Chrome's Gemini Live, Perplexity Comet, Microsoft Edge, Opera Neon, and Anthropic's Claude. By exploiting Chromium's declarativeNetRequest API to weaken security headers and redirect JavaScript resources, a malicious extension can execute code inside privileged AI contexts without any user interaction. The attack has real-world consequence: compromised AI agents could read local files, exfiltrate data, or act on behalf of victims using existing browser-level privileges.

Microsoft Uses AI to Ship Record 974-Vulnerability Patch Batch

Microsoft Uses AI to Ship Record 974-Vulnerability Patch Batch

FIRST LOOK ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 6.2 Krebs on Security

Microsoft's September 2026 Patch Tuesday delivers 974 fixes in a single release, explicitly crediting AI-assisted vulnerability discovery for the accelerated pace and volume of findings. This represents a meaningful defensive advance: AI is now closing the gap between vulnerability existence and vendor awareness, surfacing flaws faster than traditional research cycles allowed. The residual challenge is on the defender side — patch testing, prioritisation, and deployment capacity have not scaled at the same rate as AI-accelerated discovery, creating an operational backlog risk that organisations must actively manage.

FuzzingBrain V2 Discovers 29 Zero-Day Vulnerabilities

FuzzingBrain V2 Discovers 29 Zero-Day Vulnerabilities

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.8 HN AI Security

Researchers have developed FuzzingBrain V2, a multi-agent LLM system capable of autonomously discovering and reproducing software vulnerabilities with a 90% detection rate on a competitive benchmark dataset. The system discovered 29 zero-day vulnerabilities across 12 open-source projects, all confirmed by maintainers, raising both defensive and dual-use concerns for the security community. While positioned as a defensive research tool, the automation of end-to-end vulnerability discovery at this scale represents a meaningful shift in the offensive capability landscape.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.