CVE-2025-54558

OpenAI Codex CLI before 0.9.0 auto-approves ripgrep aka rg execution even with the --pre or --hostname-bin or --search-zip or -z flag...

CVE-2025-54558

OpenAI Codex CLI before 0.9.0 auto-approves ripgrep aka rg execution even with the --pre or --hostname-bin or --search-zip or -z flag...

CVE-2025-7780

The AI Engine plugin for WordPress is vulnerable to Sensitive Information Exposure in all versions up to, and including, 2.9.4. The simpleTranscribeAudio endpoint fails to restrict URL schemes before calling getaudio. This makes it possible for authenticated attackers, with Subscriber-level acces...

WordPress plugin AI Engine 信息泄露漏洞

WordPress AI Engine is a plugin based on OpenAI technology, which is mainly used to integrate artificial intelligence features into WordPress websites to improve the efficiency of content generation, automated operations and so on. WordPress AI Engine suffers from an information disclosure...

MAL-2025-6298 Malicious code in openai-fm (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 8926ff7d91a01298fc220ba494c8948e0480927fffc10ee396d0dd3bfe6ba2e0 Any computer that has this package installed or running should be considered...

Malicious code in openai-fm (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 8926ff7d91a01298fc220ba494c8948e0480927fffc10ee396d0dd3bfe6ba2e0 Any computer that has this package installed or running should be considered...

Questionnaire Mate 2.0

Questionnaire Mate is a cool script that lets you read in a list of questions and uses OpenAI to answer them based on a private knowledge base. Useful for a less informed individual to feed AI audit questions and extract proper answers...

CVE-2025-7021

Fullscreen API Spoofing and UI Redressing in the handling of Fullscreen API and UI rendering in OpenAI Operator SaaS on Web allows a remote attacker to capture sensitive user input e.g., login credentials, email addresses via displaying a deceptive fullscreen interface with overlaid fake browser...

MAL-2025-6114 Malicious code in openai-voice-agent-sdk-sample (npm)

The package communicates with a domain associated with malicious activity...

Malicious code in openai-voice-agent-sdk-sample (npm)

The package communicates with a domain associated with malicious activity...

CVE-2025-7021

CVE-2025-7021 affects OpenAI Operator SaaS on Web via the Fullscreen API handling and UI rendering, enabling a remote attacker to capture sensitive user input by presenting a deceptive fullscreen interface with overlaid fake controls and distracting elements (e.g., cookie prompts). The connected ...

CVE-2025-7021 OpenAI Operator - API Spoofing through Locking Operator on FullScreen

Fullscreen API Spoofing and UI Redressing in the handling of Fullscreen API and UI rendering in OpenAI Operator SaaS on Web allows a remote attacker to capture sensitive user input e.g., login credentials, email addresses via displaying a deceptive fullscreen interface with overlaid fake browser...

CVE-2025-7021 OpenAI Operator - API Spoofing through Locking Operator on FullScreen

Fullscreen API Spoofing and UI Redressing in the handling of Fullscreen API and UI rendering in OpenAI Operator SaaS on Web allows a remote attacker to capture sensitive user input e.g., login credentials, email addresses via displaying a deceptive fullscreen interface with overlaid fake browser...

OpenAI Operator 安全漏洞

OpenAI Operator is an AI agent for individual OpenAI developers in the United States. OpenAI Operator suffers from a security vulnerability that stems from mishandling of the full-screen API and UI rendering, which could lead to a remote attacker capturing sensitive user input via a deceptive...

PT-2025-29147 · Openai · Openai Operator Saas

Name of the Vulnerable Software and Affected Versions: OpenAI Operator SaaS on Web affected versions not specified Description: A flaw exists in the handling of the Fullscreen API and UI rendering that allows a remote attacker to capture sensitive user input, such as login credentials and email...

Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task

With today's wide adoption of LLM products like ChatGPT from OpenAI, humans and businesses engage and use LLMs on a daily basis. Like any other tool, it carries its own set of advantages and limitations. This study focuses on finding out the cognitive cost of using an LLM in the educational conte...

LangSmith Bug Could Expose OpenAI Keys and User Data via Malicious Agents

Cybersecurity researchers have disclosed a now-patched security flaw in LangChain's LangSmith platform that could be exploited to capture sensitive data, including API keys and user prompts. The vulnerability, which carries a CVSS score of 8.8 out of a maximum of 10.0, has been codenamed AgentSmi...

OpenAI Shuts Down 10 Malicious AI Ops Linked to China, Russia, Iran, N. Korea

OpenAI, a leading artificial intelligence company, has revealed it is actively fighting widespread misuse of its AI tools…...

OpenAI Bans ChatGPT Accounts Used by Russian, Iranian, and Chinese Hacker Groups

OpenAI has revealed that it banned a set of ChatGPT accounts that were likely operated by Russian-speaking threat actors and two Chinese nation-state hacking groups to assist with malware development, social media automation, and research about U.S. satellite communications technologies, among...

CVE-2025-5018

The Hive Support plugin for WordPress is vulnerable to unauthorized access and modification of data due to a missing capability check on the hsupdateaichatsettings and hivelitesupportgetallbinbox functions in all versions up to, and including, 1.2.5. This makes it possible for authenticated...