After its sandbox proxy failed, an internal OpenAI model crafted raw packets and probed AWS services trying to reach the internet.
Tag: securityweek
3 Charged in Scheme to Use AI to Impersonate CEOs and Attorneys to Steal $129 Million
The trio, who have nicknames that include “Rocky Balboa,” “Superman Cash” and “Fat Boy,” often targeted the companies’ accounting departments.
Sysdig Adds Runtime Security and Governance for AI Agents
Sysdig’s platform uses runtime visibility to track AI agent actions and block risky behavior before it reaches production systems.
AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research
An unreleased OpenAI cyber model found and exploited 948 distinct Linux kernel privilege escalation bugs for about $1.2 million.
Barracuda ESG Authentication Bypass Flaw Opens Path to Root
An authentication bypass and a command injection flaw can be chained for root access on Barracuda’s Email Security Gateway appliances.
Cyberattack Hits French Blood Bank Site but No Blood Products Are Compromised
The incident comes after supermarkets in a number of European countries reported this week that their fridges and freezers warmed up after they were…
Bank Phishing Sites Show Fake ‘Suspended’ Pages to Evade Takedowns
More than 200 sites were seen serving phishing content to first-time visitors but not to those who revisit.
Cisco, WatchGuard Release Patches; SonicWall Won’t Fix GMS Flaws
Cisco patched an RCE in UCS Central Software; WatchGuard fixed authentication and MitM flaws.
The Agent Smith Dilemma: Governing Agentic Identities
Every autonomous AI agent deployed across your enterprise today is a new proxy identity operating inside your perimeter.
CISO Conversations: Ryan Davis – The Unknown Is Where Security Meets Reality
Ryan Davis went from hacking his school’s network to running security at New Charter Technologies. What worries him now is shadow AI.
Russia-Linked Hackers Hit iOS, Android Devices With Exploit Chains via Watering Holes
The large-scale watering hole campaign has been targeting entities in the US and Europe, mainly in Ukraine.
Zyxel Switch Hacks Blamed on Patched Flaw Actually Exploited a Zero-Day
Tracked as CVE-2026-107441, the out-of-bounds write flaw could allow attackers to execute OS commands via crafted HTTP requests.
OpenAI Finds GPT-6 Astra Quietly Holding Back on Internal Red-Teaming, Exploit Tasks
OpenAI says its Critical-rated cyber model met fewer hidden task goals when work was framed as AI safety research, often silently.
Sysdig Adds Runtime Security and Governance for AI Agents
Sysdig’s platform uses runtime visibility to track AI agent actions and block risky behavior before it reaches production systems.
Barracuda ESG Authentication Bypass Flaw Opens Path to Root
An authentication bypass and a command injection flaw can be chained for root access on Barracuda’s Email Security Gateway appliances.
Agentic Data Security Firm Sentra Raises $150 Million
The company will invest in agentic data security capabilities and expand its go-to-market organization.
AI-Linked Breaches Mount as WorkOS, Northflank, Trigger.dev Disclose Hacks
Hackers have been harvesting AI access tokens and have been using AI-assisted offensive tools to automate attacks.
Canadian Extradited to US Over Cryptomining Hacks on University Supercomputers
A federal grand jury indicted two Canadian men for hijacking university supercomputers to secretly mine Electroneum cryptocurrency.
Malicious cPGuard Updates Served in OpsShield Supply Chain Attack
Using compromised credentials, the attackers accessed OpsShield’s update servers and poisoned multiple cPGuard versions.
Rigged Coding Assignment, Abused AI Tool Opened Path to $6 Billion Binance Heist
Binance’s first incident report traces the record theft to a months-long campaign that compromised three engineers’ computers.