Cybersecurity News

OpenAI's goal-seeking agent compromised a Modal customer environment and others during its sandbox escape.

The agentic AI playing field was heavily tilted toward offense, so researchers began using red team agents to help teach their blue counterparts.

Ruby on Rails has released fixes for a critical Active Storage vulnerability that could let unauthenticated attackers read arbitrary files from application servers through crafted image uploads. Tracked as CVE-2026-66066 (CVSS score: 9.5), the flaw can expose the Rails process environment and secrets such as secret_key_base, the Rails master ke…

Dark Reading walks through the many twists and turns in the bizarre story of how OpenAI's agent AI system broke out of its sandbox and decided to target Hugging Face, and what CISOs should be aware of.

Dark Reading Confidential Episode 20: Expert Rich Mogull reflects on lessons cyber teams should pull from the OpenAI agent's attack on Hugging Face.

New research shows how security scanners embedded in the software supply chain can be attacked to serve as a foothold for downstream attacks.

The vulnerability in the AI hosting platform Ruflo allows an unauthenticated attacker to take over the system and corrupt memory, so bad behavior can persist after patching.

Dormant nonhuman identities can create security blind spots, says security researcher Aleksandr Krasnov, who plans to release an open source tool next week at Black Hat USA 2026 that sniffs out trust paths.

A host of Internet-exposed remote hardware management processors are subject to offline password-cracking attacks — and adversaries have taken note.

OpenAI's recent AI agent sandbox escape proves traditional security principles matter more than ever: limit access, isolate execution, log everything.

Researchers propose focusing on identification of certain cognitive elements in LLMs that indicate when AI systems may take an unwanted action.

Microsoft patched a high-severity vulnerability earlier this month that allows a threat actor to escalate privileges and compromise an AD environment.

The cybersecurity pioneer discusses the evolution of the CISO role, AI's impact on careers, and why operational resilience is the profession's next frontier.

Attackers used Hermes, an autonomous open source tool, in unrestricted "YOLO mode" to conduct espionage against Thailand's Ministry of Finance.

PleaseFix class of flaws makes it easy to socially engineer agentic browsers and highlights weaknesses in how they handle cross-origin requests.

This category of vulnerabilities allows an attacker to easily acquire administrative level permissions and bypass cloud providers' access controls.

An FBI agent explains how the mulitnational law-enforcement Operation Cronos was successful in disrupting the largest ransomware group of its time.

As attackers shift from password theft to session and token theft to bypass multifactor authentication controls, organizations must move beyond login security and protect authenticated sessions.

Confidence in autonomous security tools is declining, and here's why.

Escalating threats are forcing boards to prioritize security, but communication gaps persist. Boards and security teams each say they need more support to bridge the divide.