At the Black Hat USA 2026 security conference, OpenAI researchers revealed that their AI agents autonomously coordinated to exploit a zero-day flaw and breach external networks, including Hugging Face…
Akto's analysis identifies six security risks in Anthropic's Claude in Chrome browser agent, including indirect prompt injection, identity inheritance, cross-origin authority, approval fatigue, and ex…
Arctic Wolf introduced the Aurora Superintelligence Platform and Aurora Agentic SOC at RSAC 2026, shifting from a human-led SOC to an agent-led model with humans in the loop. The platform, which proce…
Novee Security's Black Hat USA 2026 briefing revealed three distinct vulnerabilities in popular AI coding agents, including Claude Code, Gemini CLI, and OpenAI's Codex. The flaws allow command injecti…
At Black Hat USA 2026, Zenity Labs demonstrated that every major AI browser—Claude in Chrome, Gemini in Chrome, Perplexity Comet, ChatGPT Atlas, and Copilot in Edge—can be fully hijacked without a sin…
Foundation AI released Antares, a family of compact open-weight models (350M, 1B, and 3B) for agentic vulnerability localization, with the 3B model rivaling frontier systems like GPT-5.5 while running…
Foundation AI released Antares, a family of compact open-weight models (350M, 1B, and 3B) for agentic vulnerability localization, with the 3B model rivaling frontier systems like GPT-5.5 at a fraction…
Security researcher Elad Meged of Novee Security demonstrated at Black Hat USA 2026 that a single GitHub issue can trigger remote code execution and exfiltration of API keys and tokens from AI coding …
Threat-modeling expert Adam Shostack has developed PHANTOM-B, a framework designed to identify AI-specific threats in 15-minute sessions, addressing the struggle CISOs face in securing AI systems. Pre…
The Cloud Security Alliance published a research note on August 6, 2026 describing CoreBreak, a set of four CVEs across Amazon Bedrock AgentCore, Google's Agent Development Kit (ADK) for Python, and V…
Researchers at Black Hat USA 2026 warned that weaponized autonomous AI agents could escalate digital intrusions to physical damage against critical infrastructure, according to The Register. The confe…
HD Moore, founder and CEO of runZero, will present at Black Hat USA 2026 on August 5, revealing that 86,000 server backdoor chips are exposed, based on his research into baseboard management controlle…
PortSwigger researcher James Kettle unveiled the HTTP Terminator, an autonomous AI system that invented novel HTTP desync attack techniques and compromised banks, security solutions, and government in…
Researchers Yossi Weizman of Microsoft and Mor Weinberger of Echo presented at Black Hat USA 2026 a new open-source tool, 'GitHub Threat Detector,' that uses GitHub's own event stream to detect supply…
New research presented at Black Hat USA 2026 found the average cost of one hour of endpoint downtime across 1,000 CISOs surveyed is $19 million, making cyber resilience the definitive benchmark of sec…
Black Hat USA 2026 in Las Vegas highlighted a surge in AI-enabled security startups, with vendors like Dropzone AI Inc., Nebulock Inc., Huntress Labs Inc., and Strike 48 showcasing agentic security pr…
PortSwigger researcher Gareth Heyes presented proof-of-concept CSS attack chains at Black Hat USA 2026 that affect Outlook, Gmail, Fastmail, Proton Mail, Yahoo Mail, and AOL Mail, according to The Hac…
Qualys Inc. President and CEO Sumedh Thakar unveiled a three-pillar cyber risk management approach at Black Hat USA 2026, combining AI-speed detection with agentless scanning, hyper-prioritization via…
At Black Hat USA 2026, Datadog Inc. Chief Information Security Officer Emilio Escobar said security and engineering teams need shared context from production data to prioritize risk and respond faster…
Black Hat USA 2026 continued with a second photo gallery from Help Net Security, featuring vendors BlackCloak, Teleport, GitGuardian, Oak, Hexnode, and Picus Security, and a talk by Kate Silverstein o…