630 matches found
MAL-2025-17415 Malicious code in commitizen-gemini-magellan-cygnus (npm)
The package commitizen-gemini-magellan-cygnus was found to contain malicious code...
MAL-2025-21257 Malicious code in gemini-install-server-radioastronomy (npm)
The package gemini-install-server-radioastronomy was found to contain malicious code...
MAL-2025-26412 Malicious code in mineralogy-grus-gemini-sedna (npm)
The package mineralogy-grus-gemini-sedna was found to contain malicious code...
MAL-2025-39494 Malicious code in writable-gemini-pavo-jabbah (npm)
The package writable-gemini-pavo-jabbah was found to contain malicious code...
Fedora 41 : chromium (2025-81d05a9171)
The remote Fedora 41 host has a package installed that is affected by multiple vulnerabilities as referenced in the FEDORA-2025-81d05a9171 advisory. Updated to 139.0.7258.66 CVE-2025-8576: Use after free in Extensions CVE-2025-8578: Use after free in Cast CVE-2025-8579: Inappropriate implementati...
Fedora 42 : chromium (2025-04158e05ef)
The remote Fedora 42 host has a package installed that is affected by multiple vulnerabilities as referenced in the FEDORA-2025-04158e05ef advisory. Updated to 139.0.7258.66 CVE-2025-8576: Use after free in Extensions CVE-2025-8578: Use after free in Cast CVE-2025-8579: Inappropriate implementati...
A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection
Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new attacks, degrade model responses to benign prompts, or...
New Promptware Attack Hijacks User’s Gemini AI Via Google Calendar Invite
Cybersecurity researchers demonstrate a new attack on Google Gemini AI for Workspace. Discover how a simple calendar invite can be used to perform phishing, steal emails, and even control home appliances...
Google Chrome 安全漏洞
Google Chrome is a web browser from Google, Inc USA. A security vulnerability exists in Google Chrome that stems from an improper implementation of Gemini Live...
Browser Extensions Can Exploit ChatGPT, Gemini in ‘Man in the Prompt’ Attack
Man in the Prompt attack shows how browser extensions can exploit ChatGPT, Gemini and other AI tools to steal data or inject hidden prompts...
Improper Neutralization of Input Used for LLM Prompting
Overview @google/gemini-cli is a Gemini CLI Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting due to an improper implementation of the getCommandRoot and isCommandAllowed functions. An attacker can inject malicious commands by leveraging...
No thanks: Google lets its Gemini AI access your apps, including messages [updated]
If you're an Android user, you'll need to take action if you don’t want Google's Gemini AI to have access to your apps. That's because, regardless of your previous settings, Google now allows Gemini to interact with third-party apps. Through Gemini extensions, it already had the ability to...
Evaluation Empirique De La Sécurisation Et De L'Alignement De ChatGPT Et Gemini: Analyse Comparative Des Vulnérabilités Par Expérimentations De Jailbreaks
Large Language models LLMs are transforming digital usage, particularly in text generation, image creation, information retrieval and code development. ChatGPT, launched by OpenAI in November 2022, quickly became a reference, prompting the emergence of competitors such as Google's Gemini. However...
CVE-2024-54306
Cross-Site Request Forgery CSRF vulnerability in aitool AIKCT Engine Chatbot, ChatGPT, Gemini, GPT-4o Best AI Chatbot ai-seo-translator allows Cross Site Request Forgery.This issue affects AIKCT Engine Chatbot, ChatGPT, Gemini, GPT-4o Best AI Chatbot: from n/a through = 1.6.2...
CVE-2024-12236
A security issue exists in Vertex Gemini API for customers using VPC-SC. By utilizing a custom crafted file URI for image input, data exfiltration is possible due to requests being routed outside the VPC-SC security perimeter, circumventing the intended security restrictions of VPC-SC. No further...
ACSE-Eval: Can LLMs Threat Model Real-World Cloud Infrastructure?
While Large Language Models have shown promise in cybersecurity applications, their effectiveness in identifying security threats within cloud deployments remains unexplored. This paper introduces AWS Cloud Security Engineering Eval, a novel dataset for evaluating LLMs cloud security threat...
CVE-2022-29538
RESI Gemini-Net Web 4.2 is affected by Improper Access Control in authorization logic. An unauthenticated user is able to access some critical resources...
CVE-2022-29540
resi-calltrace in RESI Gemini-Net 4.2 is affected by Multiple XSS issues. Unauthenticated remote attackers can inject arbitrary web script or HTML into an HTTP GET parameter that reflects user input without sanitization. This exists on numerous application endpoints,...
CVE-2022-29539
resi-calltrace in RESI Gemini-Net 4.2 is affected by OS Command Injection. It does not properly check the parameters sent as input before they are processed on the server. Due to the lack of validation of user input, an unauthenticated attacker can bypass the syntax intended by the software e.g.,...