Investigating Cybersecurity Incidents Using Large Language Models in Latest-Generation Wireless Networks

The purpose of research: Detection of cybersecurity incidents and analysis of decision support and assessment of the effectiveness of measures to counter information security threats based on modern generative models. The methods of research: Emulation of signal propagation data in MIMO systems,...

Prompt Engineering Techniques with Spring AI

This blog post demonstrates practical implementations of Prompt Engineering techniques using Spring AI. The examples and patterns in this article are based on the comprehensive Prompt Engineering Guide that covers the theory, principles, and patterns of effective prompt engineering. The blog show...

Brave Software: Prompt Injection via GitHub Patch in Brave AI Chat (Leo)

Component: Brave AI Chat brave-core/components/aichat/ Severity: High Confirmed ability to override AI instructions and persona via fetched content Vulnerability Summary The Brave AI Chat feature allows fetching .patch files from GitHub pull request pages to use as context. A combination of...

CVE-2025-32018

Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the us...

CVE-2025-32018 Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs

Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the us...

CVE-2025-32018 Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs

Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the us...

CVE-2025-32018 Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs

Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the us...

SUSE CVE-2025-3035

By first using the AI chatbot in one tab and later activating it in another tab, the document title of the previous tab would leak into the chat prompt. This vulnerability was fixed in Firefox 137...

CVE-2025-3035

By first using the AI chatbot in one tab and later activating it in another tab, the document title of the previous tab would leak into the chat prompt. This vulnerability affects Firefox 137...

CVE-2025-3035

By first using the AI chatbot in one tab and later activating it in another tab, the document title of the previous tab would leak into the chat prompt. This vulnerability was fixed in Firefox 137...

CVE-2025-3035

By first using the AI chatbot in one tab and later activating it in another tab, the document title of the previous tab would leak into the chat prompt. This vulnerability affects Firefox 137...

UBUNTU-CVE-2025-3035

By first using the AI chatbot in one tab and later activating it in another tab, the document title of the previous tab would leak into the chat prompt. This vulnerability was fixed in Firefox 137...

CVE-2025-3035

Mozilla Firefox (including Firefox-ESR ) is affected by a vulnerability where the document title of a previous tab leaks into an AI chatbot prompt. This occurs when a user interacts with the chatbot in one tab and subsequently activates it in another tab. This flaw affects versions prior to 137 ....

CVE-2025-3035: Exposure of Private Personal Information to an Unauthorized Actor

By first using the AI chatbot in one tab and later activating it in another tab, the document title of the previous tab would leak into the chat prompt. This vulnerability was fixed in Firefox 137...

PT-2025-14110

Name of the Vulnerable Software and Affected Versions Firefox versions prior to 137 Description The issue occurs when the AI chatbot is used in one tab and then activated in another tab, causing the document title of the previous tab to leak into the chat prompt. Recommendations For versions prio...

ASB-A-339532378

In multiple locations, there is a possible way to mislead a user into approving an authentication prompt for one app when its result will be used in another due to a logic error in the code. This could lead to local escalation of privilege with no additional execution privileges needed. User...

CVE-2025-31124

CVE-2025-31124 (Zitadel) describes a user enumeration flaw in the login flow caused by normalization of the username when the “Ignoring unknown usernames” setting is enabled. Although the UI prompts for a password and returns “Username or Password invalid” for non-existent users, the normalizatio...

iOS Workspace App 2501.10 - How to Fix Login Hang at "Stay Signed In" Prompt

Users of the Citrix Workspace app on iOS devices may experience a hang or freeze at the "Stay Signed In" prompt after adding their Citrix Cloud workspace URL. The app becomes unresponsive, preventing users from selecting either "Allow" or "Deny."...

CVE-2025-2733

A vulnerability classified as critical has been found in mannaandpoem OpenManus up to 2025.3.13. This affects an unknown part of the file app/tool/pythonexecute.py of the component Prompt Handler. The manipulation leads to os command injection. It is possible to initiate the attack remotely. The...

LibreChat groupid parameter access control error vulnerability

LibreChat is an enhanced ChatGPT clone. An Access Control Error vulnerability exists in versions of LibreChat prior to 0.7.6, which stems from the groupid parameter not verifying that the prompt ID provided belongs to the current user, and can be exploited by an attacker to cause the deletion of...