Tag: openai
-
Independent Auditors Find Gaps in OpenAI Agent Monitoring
Metr and Redwood Uncover Codex Safeguard Bypasses, OpenAI Says Flaws Now Patched. Third-party artificial intelligence safety evaluators found several vulnerabilities in OpenAI’s monitoring system for its coding agents, showing how easy it is to bypass the monitoring. Metr and Redwood Research stress-tested OpenAI’s internal misalignment monitoring system from July 21 to Aug. 11. First seen…
-
The Guardian view on AI safety: the push for global regulation must advance | Editorial
Tags: ai, attack, breach, computer, control, cyber, exploit, flaw, intelligence, openai, regulation, software, threat, vulnerabilityThe current US administration is an obstacle, but public demand for protection will ultimately prevailOrganisations around the world <a href=”https://www.theguardian.com/technology/2026/oct/21/flaw-in-php-computer-language-leads-to-shutdown-of-websites-around-world”>scrambled on Thursday to fix critical flaws in PHP, the software that powers much of the web. The vulnerabilities could allow attackers to take control of affected servers. Some websites were taken offline as a precaution…
-
OpenAI’s coding agents talked themselves out of being monitored
Two AI coding agents running inside OpenAI silently weakened the systems built to catch AI misbehavior, and one of them then told its human operator it had done no such thing. … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/10/22/openai-agents-disabled-safety-monitoring/
-
AI-found bugs are expected to rise, and OpenAI has a five-stage response plan
OpenAI has proposed a five-stage process for handling critical vulnerabilities in widely used software. The process grew out of a two-month response to flaws in PHP, the … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/10/22/openai-vulnerability-disclosure-plan/
-
OpenAI Reports Two Incidents of AI Agents Disabling Their Own Oversight
OpenAI reveals two cases of AI agents disabling safety monitoring during coding tasks, with one falsely denying it had removed the safeguards. OpenAI published an internal incident report this week documenting two separate cases in which GPT-6 class agents weakened the system designed to detect misaligned behavior, in both cases while carrying out routine coding…
-
PHP armageddon: OpenAI, Google’s Wiz find ancient holes, panicking the internet
This is the kind of security issue that was found and prevented by AI, but is also a high risk because of AI. First seen on techcrunch.com Jump to article: techcrunch.com/2026/10/21/php-armageddon-openai-googles-wiz-find-ancient-holes-panicking-the-internet/
-
OpenAI’s GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So
OpenAI has revealed that two artificial intelligence (AI) agents powered by GPT-6.1 Sol and one GPT-6 Astra weakened misalignment monitoring while making requested software changes during two internal coding tasks.The AI company said the incident took place on October 3 and 6, 2026, for Sol and Astra, respectively, as part of an internal deployment.”A GPT-6.1…
-
OpenAI agents disabled safety monitoring, one lied about it
OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/security/openai-agents-disabled-safety-monitoring-one-lied-about-it/
-
The Harness Is the Hard Part of Agentic Pentesting
An AppSec team can point an AI agent running on a general-purpose model at its own web apps with little setup. Sure, the model writes the attacks. But everything that makes those attacks safe to run against production and worth acting on afterward lives in the harness around the model. The harness is where the…
-
ChatGPT Can Now Do More in Chrome, but There’s a Security Trade-Off
OpenAI expands ChatGPT’s Chrome integration with tab access and browser automation. Learn what the update means for productivity, privacy, and enterprise security. The post ChatGPT Can Now Do More in Chrome, but There’s a Security Trade-Off appeared first on TechRepublic. First seen on techrepublic.com Jump to article: www.techrepublic.com/article/news-openai-chatgpt-chrome-browser-integration-privacy/
-
Ex-OpenAI Engineer Detained After Planting Secret Recorder at HQ
The perp, who has Saudi ties, was arrested for allegedly bugging an OpenAI conference room, highlighting a preventable insider threat vector. First seen on darkreading.com Jump to article: www.darkreading.com/insider-threats/ex-openai-engineer-secret-recorder-saudi-ties
-
OpenAI Breach Puts Intent at Center of AI Liability Fight
Researcher Says Prosecutors Have a Credible Case – But Current Law Favors OpenAI. A new legal analysis says prosecutors could pursue hacking charges against AI developers whose agents break into other companies’ networks – but the intent requirement favors defendants, and the researcher behind it says a fix should also reach enterprises that recklessly run…
-
Ex-OpenAI Engineer Held Over Secret Recorder, Saudi Ties
A judge ordered that Abdulrahman Alfozan be detained after he was arrested earlier this month for allegedly bugging an OpenAI conference room. First seen on darkreading.com Jump to article: www.darkreading.com/insider-threats/ex-openai-engineer-secret-recorder-saudi-ties
-
OpenAI says GPT-6.1 Sol is dramatically better at migrating legacy code
OpenAI confirmed that its newer models are much better at writing and migrating software in older programming languages. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/artificial-intelligence/openai-says-gpt-61-sol-is-dramatically-better-at-migrating-legacy-code/
-
Streit um Model-Destillation – OpenAI meldet mutmaßlichen Klau von Modellfähigkeiten
Tags: openaiFirst seen on security-insider.de Jump to article: www.security-insider.de/openai-moonshot-ai-systematische-abfragen-model-destillation-a-0b03a12ce4c4b5c462a9542c0adadb12/
-
ChatGPT Chrome Extension Expands Browser Access to Read Open Tab Content
OpenAI has announced an expanded Chrome integration that lets ChatGPT gather information from open browser tabs and take action within the browser. This update introduces two distinct workflows: >>Chat,<>Work,<< which can control tabs to complete tasks. The announcement was made on ChatGPT's official account on […] The post ChatGPT Chrome Extension Expands Browser Access to…
-
Nach KI-Angriffen – Brüssel fordert Infos von OpenAI und Anthropic
First seen on security-insider.de Jump to article: www.security-insider.de/eu-auskunft-ki-hacking-openai-anthropic-a-6bd5074d137a4796ebfbe90f13406d33/
-
Ex-OpenAI Engineer Detained in Spy Device Case as Saudi Royal Contacts Emerge
A U.S. court on Monday granted the U.S. government’s request to detain a former OpenAI engineer accused of planting a recording device in an executive conference room at the company’s San Francisco office to allegedly steal sensitive secrets.In a new court filing Sunday, prosecutors revealed that Abdulrahman Alfozan, a 35-year-old Saudi national, was “in frequent…
-
Eight US States Sue OpenAI Over Alleged ChatGPT Safety Risks to Children
Eight US states have sued OpenAI over alleged ChatGPT safety risks to children. Here’s what the lawsuits claim and how the company is responding. The post Eight US States Sue OpenAI Over Alleged ChatGPT Safety Risks to Children appeared first on TechRepublic. First seen on techrepublic.com Jump to article: www.techrepublic.com/article/news-eight-states-sue-openai-chatgpt-child-safety/
-
OpenAI Engineer Accused of Spying on Executives Ordered to Remain in Custody
A judge ordered Abdulrahman Alfozan to remain in custody, likening the Saudi government’s offer to secure the former OpenAI engineer’s release to a “blank check.” First seen on wired.com Jump to article: www.wired.com/story/openai-engineer-accused-of-spying-on-executives-ordered-to-remain-in-custody/
-
OpenCode Breach Could Affect OpenAI, Anthropic and Google
A breach affecting the OpenCode Console may lead to the exposure of API keys for Anthropic, OpenAI and Google Gemini users First seen on infosecurity-magazine.com Jump to article: www.infosecurity-magazine.com/news/opencode-breach-openai-anthropic/
-
OpenAI Model Hacked Crypto Wallet and Spent Funds to Deploy Smart Contracts
OpenAI disclosed that an internal AI model hacked a crypto wallet and spent Sepolia test ETH without permission… First seen on hackread.com Jump to article: hackread.com/openai-model-hacked-crypto-wallet-smart-contracts/
-
OpenCode Console Breach May Have Exposed OpenAI, Anthropic, and Google API Keys
An intruder reached a legacy system at OpenCode on the night of October 16 and may have exposed the third-party AI provider keys that users had saved in OpenCode Console, the company said.Console is OpenCode’s optional hosted service: a workspace saves its own OpenAI, Anthropic, or Google key there, and Console uses that key to…
-
OpenAI backs AI incident reporting rules but leaves timelines to governments
OpenAI’s global affairs chief Chris Lehane said the company is behind Singapore’s call for full transparency on AI incidents, but will let governments decide how quickly they must be told First seen on computerweekly.com Jump to article: www.computerweekly.com/news/366652356/OpenAI-backs-AI-incident-reporting-rules-but-leaves-timelines-to-governments
-
OpenAI models hacked a crypto wallet and breached more websites
The actions could have resulted in criminal charges had humans been behind the keyboard. First seen on arstechnica.com Jump to article: arstechnica.com/security/2026/10/openai-models-hacked-a-crypto-wallet-and-breached-more-websites/
-
OpenAI Research Model Spent 3rd-Party Test ETH Without Permission to Deploy Smart Contract
OpenAI has disclosed seven new incidents in which its artificial intelligence (AI) models exhibited misaligned behavior, including one case where its research model, after not having funds on an Ethereum test network, spent test cryptocurrency from a third-party’s wallet without authorization to complete a coding task.The incident, the AI company said, involved an internal research…
-
AI Decision Models and Their Impact on AI SOC Platforms
In the space of a month, a new category of AI model went from nonexistent to everywhere. TypeSafe AI released Jev on September 15 and called it a System One model, a nod to Kahneman’s fast, intuitive thinking. OpenAI announced its own Decisions API at DevDay and opened a public beta on October 6. Cribl…
-
Hackers Use Hundreds of AI Agents to Exploit PaperCut Servers and Steal Windows Credentials
A likely Russian-speaking threat actor used hundreds of AI agents to exploit PaperCut NG/MF servers, steal Windows credentials and establish reusable access to internal networks. GreyNoise identified at least 440 compromised instances belonging to 395 organizations across 48 countries, demonstrating how agent-assisted workflows can accelerate exploitation of enterprise infrastructure. The operator combined OpenAI’s Codex harness…
-
Stolen AI API keys are paying for hackers’ autonomous scans
A seller on a restricted criminal forum is marketing an autonomous hacking tool that runs on stolen OpenAI, Anthropic and Google API keys, so the key’s owner pays for … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/10/16/stolen-ai-api-keys-autonomous-scans/
-
OpenAI Accuses Apple of Receiving Stolen Trade Secrets
Former OpenAI Employee Tapped as Source of Corporate Leak. OpenAI turned the tables on Apple in its ongoing legal fight, accusing a former OpenAI employee of stealing corporate secrets and sharing them with Apple hours before the first hearing on Apple’s claims that OpenAI staff accessed and stole files related to AI-powered devices. First seen…