Tag: openai
-
OpenAI über KI-Browser: Prompt-Injection-Problem wahrscheinlich nie lösbar
Gerade bei den neuen KI-Browsern gelten Prompt Injections als extrem gefährlicher Angriffsvektor. OpenAI sieht keine vollständige Lösung dafür. First seen on golem.de Jump to article: www.golem.de/news/openai-ueber-ki-browser-prompt-injection-problem-wahrscheinlich-nie-loesbar-2512-203551.html
-
OpenAI says AI browsers may always be vulnerable to prompt injection attacks
OpenAI says prompt injections will always be a risk for AI browsers with agentic capabilities, like Atlas. But the firm is beefing up its cybersecurity with an ‘LLM-based automated attacker.’ First seen on techcrunch.com Jump to article: techcrunch.com/2025/12/22/openai-says-ai-browsers-may-always-be-vulnerable-to-prompt-injection-attacks/
-
DataDome recognized in The Bot And Agent Trust Management Software Landscape, Q4 2025 from Forrester
DataDome recognized in The Bot And Agent Trust Management Software Landscape, Q4 2025 from Forrester Forrester has just released The Bot And Agent Trust Management Software Landscape, Q4 2025 report. It marks a fundamental shift to reflect the rapid rise of agentic AI traffic”, moving beyond traditional bot management to a new paradigm that establishes…
-
Cybersecurity Snapshot: Cyber Pros Emerge as Bold AI Adopters, While AI Changes Data Security Game, CSA Reports Say
Tags: advisory, ai, api, attack, awareness, business, cloud, compliance, control, credit-card, crime, crimes, crypto, cyber, cybersecurity, data, data-breach, defense, detection, exploit, finance, framework, google, governance, guide, healthcare, injection, intelligence, law, LLM, lockbit, malicious, metric, mitigation, monitoring, network, office, openai, ransom, ransomware, risk, risk-management, service, skills, sql, threat, tool, training, update, vulnerabilityFormerly “AI shy” cyber pros have done a 180 and become AI power users, as AI forces data security changes, the CSA says. Plus, PwC predicts orgs will get serious about responsible AI usage in 2026, while the NCSC states that, no, prompt injection isn’t the new SQL injection. And much more! Key takeaways Cyber…
-
Cybersecurity Snapshot: Cyber Pros Emerge as Bold AI Adopters, While AI Changes Data Security Game, CSA Reports Say
Tags: advisory, ai, api, attack, awareness, business, cloud, compliance, control, credit-card, crime, crimes, crypto, cyber, cybersecurity, data, data-breach, defense, detection, exploit, finance, framework, google, governance, guide, healthcare, injection, intelligence, law, LLM, lockbit, malicious, metric, mitigation, monitoring, network, office, openai, ransom, ransomware, risk, risk-management, service, skills, sql, threat, tool, training, update, vulnerabilityFormerly “AI shy” cyber pros have done a 180 and become AI power users, as AI forces data security changes, the CSA says. Plus, PwC predicts orgs will get serious about responsible AI usage in 2026, while the NCSC states that, no, prompt injection isn’t the new SQL injection. And much more! Key takeaways Cyber…
-
OpenAI Launches GPT-5.2-Codex for Secure Coding
OpenAI has launched GPT-5.2-Codex, an agentic coding model that boosts real-world software engineering and AI-powered vulnerability research. First seen on esecurityplanet.com Jump to article: www.esecurityplanet.com/threats/openai-launches-gpt-5-2-codex-for-secure-coding/
-
OpenAI’s GPT-5.2 Codex Boosts Agentic Coding and Cyber Vulnerability Detection
OpenAI has officially released GPT-5.2-Codex, marking a significant leap forward in AI-driven software engineering and defensive cybersecurity. Described as the most advanced >>agentic
-
What the Latest OpenAI Security Breach Reveals About the State of AI Protection
A recent OpenAI-related breach via third-party provider Mixpanel exposes how AI supply chain vulnerabilities enable phishing, impersonation, and regulatory risk”, even without direct system compromise. First seen on securityboulevard.com Jump to article: securityboulevard.com/2025/12/what-the-latest-openai-security-breach-reveals-about-the-state-of-ai-protection/
-
What the Latest OpenAI Security Breach Reveals About the State of AI Protection
A recent OpenAI-related breach via third-party provider Mixpanel exposes how AI supply chain vulnerabilities enable phishing, impersonation, and regulatory risk”, even without direct system compromise. First seen on securityboulevard.com Jump to article: securityboulevard.com/2025/12/what-the-latest-openai-security-breach-reveals-about-the-state-of-ai-protection/
-
Featured Chrome Browser Extension Caught Intercepting Millions of Users’ AI Chats
A Google Chrome extension with a “Featured” badge and six million users has been observed silently gathering every prompt entered by users into artificial intelligence (AI)-powered chatbots like OpenAI ChatGPT, Anthropic Claude, Microsoft Copilot, DeepSeek, Google Gemini, xAI Grok, Meta AI, and Perplexity.The extension in question is Urban VPN Proxy, which has a 4.7 rating…
-
Security for AI: How Shadow AI, Platform Risks, and Data Leakage Leave Your Organization Exposed
Tags: access, ai, attack, awareness, business, chatgpt, china, cloud, compliance, control, corporate, cybersecurity, data, data-breach, defense, detection, endpoint, governance, guide, infrastructure, injection, leak, LLM, malicious, microsoft, mitigation, monitoring, network, open-source, openai, privacy, RedTeam, risk, saas, service, strategy, threat, tool, training, vulnerabilityYour employees are using AI whether you’ve sanctioned it or not. And even if you’ve carefully vetted and approved an enterprise-grade AI platform, you’re still at risk of attacks and data leakage. Key takeaways: Security teams face three key risks as AI usage becomes widespread at work: Shadow AI, the challenge of safely sanctioning tools,…
-
Security for AI: How Shadow AI, Platform Risks, and Data Leakage Leave Your Organization Exposed
Tags: access, ai, attack, awareness, business, chatgpt, china, cloud, compliance, control, corporate, cybersecurity, data, data-breach, defense, detection, endpoint, governance, guide, infrastructure, injection, leak, LLM, malicious, microsoft, mitigation, monitoring, network, open-source, openai, privacy, RedTeam, risk, saas, service, strategy, threat, tool, training, vulnerabilityYour employees are using AI whether you’ve sanctioned it or not. And even if you’ve carefully vetted and approved an enterprise-grade AI platform, you’re still at risk of attacks and data leakage. Key takeaways: Security teams face three key risks as AI usage becomes widespread at work: Shadow AI, the challenge of safely sanctioning tools,…
-
OpenAI Enhances Defensive Models to Mitigate Cyber-Threats
OpenAI has reported a surge in performance as GPT-5.1-Codex-Max reaching 76% in capability assessments, and warned of upcoming cyber-risks First seen on infosecurity-magazine.com Jump to article: www.infosecurity-magazine.com/news/openai-enhances-defensive-models/
-
OpenAI Flags Rising Cyber Risks as AI Capabilities Advance
OpenAI has issued a cautionary statement that its forthcoming AI models could present “high” cybersecurity risks as their capabilities rapidly advance. The warning, published on Wednesday, noted the potential for these AI models to either develop zero-day exploits against well-defended systems or assist in enterprise or industrial intrusion operations with tangible real-world consequences. First seen on thecyberexpress.com Jump to…
-
OpenAI Flags Rising Cyber Risks as AI Capabilities Advance
OpenAI has issued a cautionary statement that its forthcoming AI models could present “high” cybersecurity risks as their capabilities rapidly advance. The warning, published on Wednesday, noted the potential for these AI models to either develop zero-day exploits against well-defended systems or assist in enterprise or industrial intrusion operations with tangible real-world consequences. First seen on thecyberexpress.com Jump to…
-
2025 Year of Browser Bugs Recap:
Tags: access, ai, api, attack, authentication, awareness, browser, cctv, chrome, cloud, communications, computer, credentials, crypto, cyber, data, data-breach, detection, edr, email, endpoint, exploit, flaw, gartner, google, guide, identity, injection, leak, login, malicious, malware, network, openai, passkey, password, phishing, ransom, ransomware, risk, saas, service, threat, tool, update, vulnerability, windows, xss, zero-dayAt the beginning of this year, we launched the Year of Browser Bugs (YOBB) project, a commitment to research and share critical architectural vulnerabilities in the browser. Inspired by the iconic Months of Bugs tradition in the 2000s, YOBB was started with a similar purpose”Š”, “Što drive awareness and discussion around key security gaps and…
-
KI-Browser gefährden Unternehmen
Experten warnen vor der Nutzung von KI-Browsern in Unternehmen.Die Gartner-Analysten Dennis Xu, Evgeny Mirolyubov und John Watts empfehlen Unternehmen dringend, alle KI-Browser aufgrund der Cybersicherheitsrisiken auf absehbare Zeit zu blockieren. Sie stützten ihre Empfehlung auf bereits identifizierte Risiken ‘und andere potenzielle Risiken, die noch entdeckt werden müssen, da es sich um eine sehr junge Technologie…
-
KI-Browser gefährden Unternehmen
Experten warnen vor der Nutzung von KI-Browsern in Unternehmen.Die Gartner-Analysten Dennis Xu, Evgeny Mirolyubov und John Watts empfehlen Unternehmen dringend, alle KI-Browser aufgrund der Cybersicherheitsrisiken auf absehbare Zeit zu blockieren. Sie stützten ihre Empfehlung auf bereits identifizierte Risiken ‘und andere potenzielle Risiken, die noch entdeckt werden müssen, da es sich um eine sehr junge Technologie…
-
Gemini for Chrome gets a second AI agent to watch over it
Google’s two-model defense: To address these risks, Google’s solution splits the work between two AI models. The main Gemini model reads web content and decides what actions to take. The user alignment critic sees only metadata about proposed actions, not the web content that might contain malicious instructions.”This component is architected to see only metadata…
-
Kritische Sicherheitslücke CVE-2025-61260 in OpenAI Codex CLI
Kleiner Infosplitter, der mir von den Sicherheitsforschern von Check Point Research (CPR) zugegangen ist. Die sind kürzlich in OpenAIs Codex CLI auf die kritische Sicherheitslücke CVE-2025-61260 gestoßen. Diese ermöglichte Angriffe über lokale Projektdateien, stille Code-Ausführung, Infiltration und Datenklau. Was ist … First seen on borncity.com Jump to article: www.borncity.com/blog/2025/12/09/kritische-sicherheitsluecke-cve-2025-61260-in-openai-codex-cli/
-
Kritische Lücke in OpenAI Codex CLI: Unsichtbarer Lieferketten-Angriff gefährdete Entwickler weltweit
Die Security-Forscher von Check Point Research (CPR), der Analyseabteilung von Check Point Software Technologies Ltd. (NASDAQ: CHKP), haben eine schwerwiegende Verwundbarkeit im Command-Line-Tool OpenAI Codex CLI entdeckt. First seen on infopoint-security.de Jump to article: www.infopoint-security.de/kritische-luecke-in-openai-codex-cli-unsichtbarer-lieferketten-angriff-gefaehrdete-entwickler-weltweit/a43095/
-
Schwachstelle in OpenAI-Codex-CLI ermöglicht kritische Remote-Code-Execution
Die Sicherheitsforscher von Check Point Research (CPR), der IT-Forensik von Check Point Software Technologies, haben eine schwerwiegende Schwachstelle in OpenAI-Codex-CLI entdeckt. Dabei handelt es sich um das Command-Line-Tool von OpenAI, das KI-gestützte Programmierfunktionen direkt in Entwickler-Workflows integriert. Die Schwachstelle ermöglichte Remote-Code-Execution (RCE) allein durch das Öffnen eines manipulierten Projektordners und ohne Interaktion oder Zustimmung des…
-
OpenAI denies rolling out ads on ChatGPT paid plans
ChatGPT is allegedly showing ads to those who pay $20 for the Plus subscription, but OpenAI says this is an app recommendation feature, not an ad. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/artificial-intelligence/openai-denies-rolling-out-ads-on-chatgpt-paid-plans/
-
More evidence your AI agents can be turned against you
Aikido found that AI coding tools from Google, Anthropic, OpenAI and others regularly embed untrusted prompts into software development workflows. First seen on cyberscoop.com Jump to article: cyberscoop.com/ai-coding-tools-can-be-turned-against-you-aikido-github-prompt-injection/