Emoji-Based Jailbreaking of Large Language Models

Large Language Models LLMs are integral to modern AI applications, but their safety alignment mechanisms can be bypassed through adversarial prompt engineering. This study investigates emoji-based jailbreaking, where emoji sequences are embedded in textual prompts to trigger harmful and unethical...

WordPress AI Power: Complete AI Pack plugin <= 1.8.96 - Authenticated (Admin+) PHP Object Injection via wpaicg_export_prompts vulnerability

Authenticated Admin+ PHP Object Injection via wpaicgexportprompts vulnerability discovered by Tran Anh Duc in WordPress Plugin GPT3 AI Content Writer versions = 1.8.96...

Jailbreaking Attacks Vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?

As large language models LLMs are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies reporting high success rates in evading common LLMs. However,...

VulnCheck KEV: CVE-2025-49619

Skyvern through 0.1.85 is vulnerable to server-side template injection SSTI in the Prompt field of workflow blocks such as the Navigation v2 Block. Improper sanitization of Jinja2 template input allows authenticated users to inject crafted expressions that are evaluated on the server, leading to...

Italy Fines Apple €98.6 Million Over ATT Rules Limiting App Store Competition

Apple has been fined €98.6 million $116 million by Italy's antitrust authority after finding that the company's App Tracking Transparency ATT privacy framework restricted App Store competition. The Italian Competition Authority Autorità Garante della Concorrenza e del Mercato, or AGCM said the...

Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model LLM-based systems. We present an efficient and systematically evaluated defense architecture that mitigates these threats through a lightweight, multi-stage pipeline. Its core component is a...

DREAM: Dynamic Red-Teaming across Environments for AI Models

Large Language Models LLMs are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static, single-turn assessments that miss vulnerabilities from adaptive,...

CVE-2025-67849

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

New Exam Security Questions in the AI Era: Comparing AI-Generated Item Similarity between Naive and Detail-Guided Prompting Approaches

Large language models LLMs have emerged as powerful tools for generating domain-specific multiple-choice questions MCQs, offering efficiency gains for certification boards but raising new concerns about examination security. This study investigated whether LLM-generated items created with...

EUVD-2025-204305

An authentication bypass vulnerability exists in AnythingLLM v1.8.5 in via the /api/workspaces endpoint. The endpoint fails to implement proper authentication checks, allowing unauthenticated remote attackers to enumerate and retrieve detailed information about all configured workspaces. Exposed...

Kimsuky Spreads DocSwap Android Malware via QR Phishing Posing as Delivery App

The North Korean threat actor known as Kimsuky has been linked to a new campaign that distributes a new variant of Android malware called DocSwap via QR codes hosted on phishing sites mimicking Seoul-based logistics firm CJ Logistics formerly CJ Korea Express. "The threat actor leveraged QR codes...

PT-2025-52256

Name of the Vulnerable Software and Affected Versions AnythingLLM version 1.8.5 Description An authentication bypass allows unauthenticated remote attackers to enumerate and retrieve detailed information about all configured workspaces. The issue is due to missing authentication checks in the...

CVE-2025-63390

An authentication bypass vulnerability exists in AnythingLLM v1.8.5 in via the /api/workspaces endpoint. The endpoint fails to implement proper authentication checks, allowing unauthenticated remote attackers to enumerate and retrieve detailed information about all configured workspaces. Exposed...

Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models

This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model LLM safety evaluation from a constrained example-based approach to a more expansive and effective policy-based framework. By leveraging an attack LLM to generate a high volume of...

CVE-2025-63390

An authentication bypass vulnerability exists in AnythingLLM v1.8.5 in via the /api/workspaces endpoint. The endpoint fails to implement proper authentication checks, allowing unauthenticated remote attackers to enumerate and retrieve detailed information about all configured workspaces. Exposed...

CVE-2025-63390

An authentication bypass vulnerability exists in AnythingLLM v1.8.5 in via the /api/workspaces endpoint. The endpoint fails to implement proper authentication checks, allowing unauthenticated remote attackers to enumerate and retrieve detailed information about all configured workspaces. Exposed...

Featured Chrome Browser Extension Caught Intercepting Millions of Users' AI Chats

A Google Chrome extension with a "Featured" badge and six million users has been observed silently gathering every prompt entered by users into artificial intelligence AI-powered chatbots like OpenAI ChatGPT, Anthropic Claude, Microsoft Copilot, DeepSeek, Google Gemini, xAI Grok, Meta AI, and...

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

Finetuning pretrained large language models LLMs has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak vulnerabilities from their pretrained sources. We investigat...

Arbitrary SQL Execution

Neuron is vulnerable to arbitrary SQL execution. The vulnerability is due to the MySQLWriteTool executing caller‑provided SQL using PDO::prepare and execute without semantic restrictions, where an attacker can inject destructive statements such as DROP TABLE, TRUNCATE, DELETE, or ALTER via...

CVE-2025-66451

LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, when creating prompts, JSON requests are sent to define and modify the prompts via PATCH endpoint for prompt groups /api/prompts/groups/:groupId. However, the request bodies are not sufficiently validated for prop...