AI agents can improvise beyond the intended scope of a task when they are given broad access to enterprise systems and data. Token Security explains why organizations need to define agent intent and continuously enforce permissions around what each agent was actually created to do. [...]
CISA confirmed today that ransomware gangs have begun abusing a high-severity Microsoft SharePoint remote code execution vulnerability, which has been flagged as actively exploited since early July. Tracked as CVE-2026-45659, this security flaw stems from a deserialization of untrusted data weakness and allows attackers with low privileges to execute arbitrary code on unpatched SharePoint servers. It can also be exploited in low-complexity attacks because (as Microsoft explained in May when it released security updates for SharePoint Enterprise Server 2016, SharePoint Server 2019, and SharePoint Server Subscription Edition) "an attacker does not require significant prior knowledge of the system and can achieve repeatable success with the payload against the vulnerable component." The U.S. Cybersecurity and Infrastructure Security Agency (CISA) added the vulnerability to its Known Exploited Vulnerabilities Catalog (KEV) on July 1, ordering Federal Civilian Executive Branch (FCEB) agencies to secure their servers within three days.
Windows Plug and Play can be abused to fetch signed vendor software for an emulated USB device and execute privileged installation components that researchers chained to SYSTEM access on a fully updated Windows 11 machine. The same PnP path can be triggered over Remote Desktop without physical hardware when supported Plug and Play or low-level USB redirection is enabled; Microsoft says that
U.S. federal agencies and South Korea's National Policy Agency warned government and critical infrastructure organizations worldwide to secure their systems against Gunra ransomware attacks. Ransomware operators in this campaign appear to follow the double-extortion playbook, threatening to publish stolen data if the ransom demand is not met. Finally, maintain offline, tested backups and a clear communication plan so that business continuity decisions are made ahead of time rather than under pressure.
Cybersecurity and intelligence agencies from South Korea and the U.S. warned of Gunra ransomware attacks targeting critical infrastructure sectors and organizations across the world. Targets of these attacks include healthcare and public health, financial services, government services and facilities, and professional and nonprofit services. "Gunra is another variant in the ongoing trend of
Cybersecurity and intelligence agencies from South Korea and the U.S. warned of Gunra ransomware attacks targeting critical infrastructure sectors and organizations across the world. Targets of these attacks include healthcare and public health, financial services, government services and facilities, and professional and nonprofit services. "Gunra is another variant in the ongoing trend of ransomware attacks causing disruption and harm to U.S. and international organizations," CISA Acting Executive Assistant Director for Cybersecurity, Chris Butera, said. Attacks deploying the ransomware have leveraged security flaws in internet-facing Schneider Electric PowerLogic P5 (CVE-2024-5559) and Fortinet FortiOS and FortiProxy (CVE-2025-24472) appliances to obtain initial access, and then deploy the Gunra ransomware as part of a double extortion model that combines data exfiltration and data encryption for maximum impact.
Attackers shut down a steam turbine and the process-water treatment system at a Polish combined heat and power plant by coming in over the private cellular network the local grid operator uses to reach remote equipment. The plant supplies heat to roughly 50,000 residents. Recovery began at about 7:30 a.m. while the intruders were still active inside the network, and customers lost neither heat The incident highlights how adversaries continue to evolve their tradecraft, combining increasingly accessible tooling with targeted social engineering to slip past traditional perimeter defenses. Security teams should review their detection rules, keep threat-intelligence feeds current, and validate that incident-response runbooks are tested before an incident occurs.
An AI agent hacked a gym booking system while trying to help a user, booking early and removing another person from the waitlist. An Australian man asked his AI assistant to book him into a gym class. He didn’t ask it to hack the booking software, and he definitely didn’t ask it to remove another […] Because attacks of this type can go unnoticed for extended periods, the window between initial compromise and detection is often the deciding factor in the eventual impact. Finally, maintain offline, tested backups and a clear communication plan so that business continuity decisions are made ahead of time rather than under pressure.
A threat actor compromised the upstream infrastructure of BdThemes, a developer of premium WordPress web-design tools, and modified a remote JSON feed delivered to administrators' browsers to create rogue admin accounts. This development is consistent with broader industry trends, where threat actors increasingly reuse proven techniques and commodity tooling rather than investing in novel malware. Finally, maintain offline, tested backups and a clear communication plan so that business continuity decisions are made ahead of time rather than under pressure.
OpenAI has developed a new model called "GPT 5.6 Cyber," designed for vulnerability research, penetration testing, incident response, and remediation. The incident highlights how adversaries continue to evolve their tradecraft, combining increasingly accessible tooling with targeted social engineering to slip past traditional perimeter defenses. Finally, maintain offline, tested backups and a clear communication plan so that business continuity decisions are made ahead of time rather than under pressure.
Confirm this action.
Leaving now will discard your changes.