5401 matches found
CVE-2025-64495 Open WebUI vulnerable to Stored DOM XSS via prompts when 'Insert Prompt as Rich Text' is enabled resulting in ATO/RCE
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. In versions 0.6.34 and below, the functionality that inserts custom prompts into the chat window is vulnerable to DOM XSS when 'Insert Prompt as Rich Text' is enabled, since the prompt body is...
CVE-2025-64495
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. In versions 0.6.34 and below, the functionality that inserts custom prompts into the chat window is vulnerable to DOM XSS when 'Insert Prompt as Rich Text' is enabled, since the prompt body is...
CVE-2025-64495
Open WebUI (self-hosted offline AI platform) is affected by a Stored DOM XSS in RichTextInput when the “Insert Prompt as Rich Text” option is enabled. In versions 0.6.34 and earlier, the prompt body is parsed with marked.parse and then assigned to a temporary div’s innerHTML without sanitisation,...
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...
Open WebUI 跨站脚本漏洞
Open WebUI is an extensible, feature-rich, user-friendly self-hosted WebUI from Open WebUI open source. A cross-site scripting vulnerability exists in Open WebUI version 0.6.34 and earlier, which stems from a failure to clean up the prompt body when assigning it to the DOM receiver innerHtml, whi...
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...
CVE-2025-64495: Improper Neutralization of Input During Web Page Generation
Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. In versions 0.6.34 and below, the functionality that inserts custom prompts into the chat window is vulnerable to DOM XSS when 'Insert Prompt as Rich Text' is enabled, since the prompt body is...
Cross-site Scripting (XSS)
Overview open-webui is an Open WebUI Affected versions of this package are vulnerable to Cross-site Scripting XSS via the replaceCommandWithText function, by allowing user-controlled HTML from a prompt body to be passed to tempDiv.innerHTML without proper sanitization. An attacker can execute...
GHSA-W7XJ-8FX7-WFCH Open WebUI vulnerable to Stored DOM XSS via prompts when 'Insert Prompt as Rich Text' is enabled resulting in ATO/RCE
Summary The functionality that inserts custom prompts into the chat window is vulnerable to DOM XSS when 'Insert Prompt as Rich Text' is enabled, since the prompt body is assigned to the DOM sink .innerHtml without sanitisation. Any user with permissions to create prompts can abuse this to plant ...
CVE-2025-60541
A Server-Side Request Forgery SSRF in the /api/proxy/ component of linshenkx prompt-optimizer v1.3.0 to v1.4.2 allows attackers to scan internal resources via a crafted request...
PT-2025-45527
Name of the Vulnerable Software and Affected Versions Open WebUI versions 0.6.34 and below Description Open WebUI, a self-hosted artificial intelligence platform designed for offline operation, contains a Stored DOM XSS issue. When the 'Insert Prompt as Rich Text' functionality is enabled, the...
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...
EUVD-2025-38155
A Server-Side Request Forgery SSRF in the /api/proxy/ component of linshenkx prompt-optimizer v1.3.0 to v1.4.2 allows attackers to scan internal resources via a crafted request...
CVE-2025-60541
A Server-Side Request Forgery SSRF in the /api/proxy/ component of linshenkx prompt-optimizer v1.3.0 to v1.4.2 allows attackers to scan internal resources via a crafted request...
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...
From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting
As the role of Large Language Models LLM-based coding assistants in software development becomes more critical, so does the role of the bugs they generate in the overall cybersecurity landscape. While a number of LLM code security benchmarks have been proposed alongside approaches to improve the...
Prompt Optimizer 安全漏洞
Prompt Optimizer is a prompt word optimizer by and Alchemy Time Personal Developer. A security vulnerability exists in Prompt Optimizer versions 1.3.0 through 1.4.2, which stems from a server-side request forgery in the /api/proxy component, which could allow an attacker to scan internal resource...
PT-2025-45351
Name of the Vulnerable Software and Affected Versions linshenkx prompt-optimizer versions 1.3.0 through 1.4.2 Description A Server-Side Request Forgery SSRF exists in the /api/proxy/ component. This allows attackers to scan internal resources by sending a specially crafted request. The api/proxy...
