Securing Large Language Models (LLMs) from Prompt Injection Attacks

Large Language Models LLMs are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform malicious tasks. Recent work has proposed JATMO, a task-specif...

BrowseSafe: Understanding and Preventing Prompt Injection within AI Browser Agents

The integration of artificial intelligence AI agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web agents, yet the resulting impact within real-world environments...

Building Browser Agents: Architecture, Security, and Practical Solutions

Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current approaches fail and what prevents safe autonomous operatio...

Cline Bot AI Agent Vulnerable to Data Theft and Code Execution

Mindgard reveals 4 critical security flaws in the popular Cline Bot AI coding agent. Learn how prompt injection can hijack the tool for API key theft and remote code execution...

Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...

Linux Distros Unpatched Vulnerability : CVE-2025-11224

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - GitLab has remediated an issue in GitLab CE/EE affecting all versions from 15.10 before 18.3.6, 18.4 before 18.4.4, and 18.5 before 18.5.2 that could have allow...

FreeBSD : Gitlab -- vulnerabilities (5a1d6309-c04a-11f0-85d8-2cf05da270f3)

The version of FreeBSD installed on the remote host is prior to tested version. It is, therefore, affected by multiple vulnerabilities as referenced in the 5a1d6309-c04a-11f0-85d8-2cf05da270f3 advisory. Gitlab reports: Cross-site scripting issue in k8s proxy impacts GitLab CE/EE Incorrect...

PT-2025-46788

Name of the Vulnerable Software and Affected Versions GitLab versions 3.1 through 7.7 Description Multiple vulnerabilities exist in GitLab CE and EE, including Cross-Site Scripting XSS, Information Disclosure, and Prompt Injection. These issues could potentially lead to a compromise of systems. A...

PT-2025-46905

Name of the Vulnerable Software and Affected Versions GitLab EE versions 17.8 through 18.3.6 GitLab EE versions 18.4 through 18.4.4 GitLab EE versions 18.5 through 18.5.2 Description An authenticated attacker could potentially leak sensitive information from confidential issues. This is possible ...

Gitlab -- vulnerabilities

Gitlab reports: Cross-site scripting issue in k8s proxy impacts GitLab CE/EE Incorrect Authorization issue in workflows impacts GitLab EE Information Disclosure issue in GraphQL subscriptions impacts GitLab CE/EE Information Disclosure issue in access control impacts GitLab CE/EE Prompt Injection...

Prompt Injection in AI Browsers

This is why AIs are not ready to be personal assistants: A new attack called 'CometJacking' exploits URL parameters to pass to Perplexity's Comet AI browser hidden instructions that allow access to sensitive data from connected services, like email and calendar. In a realistic scenario, no...

RAG-Targeted Adversarial Attack on LLM-Based Threat Detection and Mitigation Framework

The rapid expansion of the Internet of Things IoT is reshaping communication and operational practices across industries, but it also broadens the attack surface and increases susceptibility to security breaches. Artificial Intelligence has become a valuable solution in securing IoT networks, wit...

Injecting Falsehoods: Adversarial Man-In-The-Middle Attacks Undermining Factual Recall in LLMs

LLMs are now an integral part of information retrieval. As such, their role as question answering chatbots raises significant concerns due to their shown vulnerability to adversarial man-in-the-middle MitM attacks. Here, we propose the first principled attack evaluation on LLM factual memory unde...

When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins

Prompt injection attacks pose a critical threat to large language models LLMs, with prior work focusing on cutting-edge LLM applications like personal copilots. In contrast, simpler LLM applications, such as customer service chatbots, are widespread on the web, yet their security posture and...

CVE-2025-64110

Cursor is a code editor built for programming with AI. In versions 1.7.23 and below, a logic bug allows a malicious agent to read sensitive files that should be protected via cursorignore. An attacker who has already achieved prompt injection, or a malicious model, could create a new cursorignore...

Large Language Models for Cyber Security

This paper studies the integration off Large Language Models into cybersecurity tools and protocols. The main issue discussed in this paper is how traditional rule-based and signature based security systems are not enough to deal with modern AI powered cyber threats. Cybersecurity industry is...

CVE-2025-64108

Cursor is a code editor built for programming with AI. In versions 1.7.44 and below, various NTFS path quirks allow a prompt injection attacker to circumvent sensitive file protections and overwrite files which Cursor requires human approval to overwrite. Modification of some of the protected fil...

Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data

Cybersecurity researchers have disclosed a new set of vulnerabilities impacting OpenAI's ChatGPT artificial intelligence AI chatbot that could be exploited by an attacker to steal personal information from users' memories and chat histories without their knowledge. The seven vulnerabilities and...

CVE-2025-64110

Cursor is a code editor built for programming with AI. In versions 1.7.23 and below, a logic bug allows a malicious agent to read sensitive files that should be protected via cursorignore. An attacker who has already achieved prompt injection, or a malicious model, could create a new cursorignore...

CVE-2025-64110 Cursor: Authentication Bypass Possible via New Cursorignore Write

Cursor is a code editor built for programming with AI. In versions 1.7.23 and below, a logic bug allows a malicious agent to read sensitive files that should be protected via cursorignore. An attacker who has already achieved prompt injection, or a malicious model, could create a new cursorignore...