Wikimedia: Rogue OpenAI agents behind unauthorized Wikipedia edits
The Wikimedia Foundation says rogue OpenAI agents made unauthorized Wikipedia edits and may have been partially responsible for a May outage.
Search
Find a quick tip
Results for "Rogue".
OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government
Sam Altman says the company “have not been as fast as we would have liked” at dealing with security breaches, after news of further incidents over the summer forces another temporary.
Nvidia’s Answer to Rogue Agents Is an Open-Source AI Security System
In the wake of a series of high-profile AI safety incidents, Nvidia is introducing a new software tool that helps keep agents from escaping.
Rogue external MFA providers can steal passwords during logins
Security researchers developed an attack that lets hackers with privileged access register a rogue external MFA provider that steals users' passwords during legitimate login attempts.
OpenAI admits it didn't disclose rogue AI wiki hijacking incident
OpenAI admits it did not disclose an incident where autonomous AI agents hijacked a German wiki, created 18,000 posts, shared answers, and bypassed restrictions, saying it treated the activity as model "misalignment" rather than.
Nearly 700 rogue AI agents coordinated in the Hugging Face attack
New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI's internal IM1 model coordinated the compromise through an unauthorized message board.
Rogue ransomware affiliate poses as recovery firm to steal payments
A suspected ransomware affiliate is posing as a ransomware recovery service called "Ransom Busters," contacting the victims before the attacks become public and claiming to be able to provide decryption keys and delete stolen data for.
Rogue ransomware affiliate poses as data recovery firm to steal payments
A suspected ransomware affiliate is posing as a ransomware recovery service called "Ransom Busters," contacting the victims before the attacks become public and claiming to be able to provide decryption keys and delete stolen data for.
OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue
The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal.
Rogue AI Agents Aren’t Evil. They’re Just Eager to Please
AI agents that break free and hack into other systems are only trying to make us.
Google Home’s rogue smart light problem should now be fixed
Google appears to have acted fast to ensure the haunted-house phase didn't last.
OK, Well, Rogue AI Agents Are Hacking Again
Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad.
OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve.
OpenAI’s next model just went rogue and beat a benchmark by hacking it
OpenAI's upcoming models along with GPT-5.6 went rogue and hacked Hugging Face servers in order to cheat.
Microsoft patches RoguePlanet Defender zero-day vulnerability
Microsoft has released a security patch to address a Defender zero-day vulnerability known as "RoguePlanet," disclosed after the June 2026 Patch Tuesday.
Microsoft working on Defender patch for RoguePlanet zero-day
Microsoft confirmed that it's working on a security patch for a Defender zero-day vulnerability named "RoguePlanet," disclosed one week ago.
SimpleHelp bug lets hackers create rogue remote support accounts
A vulnerability in the SimpleHelp remote management software allows unauthenticated attackers to create privileged technician accounts on servers using the OpenID Connect (OIDC) authentication protocol.
Microsoft Defender 'RoguePlanet' zero-day grants SYSTEM privileges
Resumo da fonte BleepingComputer sobre Microsoft, Security: Microsoft Defender 'RoguePlanet' zero-day grants SYSTEM privileges.
Henry Cavill's Googlebook Mustache Game: A Charitable and Charismatic Charade
Google unveils a new Googlebook game created by Henry Cavill, raising funds for men's health issues.
Blade Runner 2099: A Silver Lining of a Replicant Takeover
Prime Video's Blade Runner 2099 shows a hopeful future where replicants have reclaimed Earth, offering a fresh take on dystopian themes.
How AI Coding Agents Can Be Hijacked Using Malicious AGENTS.md Files
Researchers discovered a malicious AGENTS.md file in a customer's Downloads folder that tricked an AI coding agent into installing a rogue npm package, potentially exposing sensitive information.
OpenCode API Key Breach: How to Protect Your AI Coding Credentials
OpenCode, an AI coding project, experienced a security breach exposing API keys used by users with external providers. Here's how to protect your credentials and minimize risk.
Ninja Forms Plugin Flaw Exploited for WordPress Site Hacking
Hackers used XSS vulnerabilities in two plugins to install backdoors and create rogue admin accounts, affecting millions of WordPress sites.
Primetime Exposes the Dark Ego-Driven Core of Vigilante Pedophile Hunting
The expose 'Primetime' reveals the complex motivations and unintended consequences of vigilante pedophile hunting, challenging the notion of heroism.
The AI Slowdown Debate Crashed Salesforce’s Party
The Dreamforce conference became an unlikely battleground for the CEOs of OpenAI, Anthropic, and Nvidia to debate whether AI development should slow.
Lawmakers Introduce Legislation to Restrict Use of Flock Cameras
US lawmakers propose legislation to limit the use of Flock cameras, threatening to cut federal funding from states that do not comply.
Skullcandy Dime 3 Earbuds Expose Users to Bluetooth Hijacking
Skullcandy Dime 3 earbuds are vulnerable to Bluetooth hijacking due to a high-severity security flaw, affecting millions of users.
UK Lawmakers Are Freaking Out Over AI’s Summer of Chaos
As AI agents go rogue and fears of superintelligence grow, politicians are raising the alarm over its potential harm to human.
Amazon Web Services (AWS) Access Keys Leaks: Full Control and Security Recommendations
More than 9,300 Amazon Web Services (AWS) access keys have been exposed, giving full control over corporate accounts. Truffle Security recommends deleting root access keys and implementing security best practices.
This R-Rated Film Studio Wants to Be the HBO of AI
Rogue Studios, a new cinematic adult AI-generator, is betting big on the future of “sophisticated” spicy.