CVE-2025-46059: Improper Control of Generation of Code

langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the Supplier because the...

Hacker Added Prompt to Amazon Q to Erase Files and Cloud Data

A hacker injected a malicious prompt into Amazon Q via GitHub, aiming to delete user files and wipe AWS data, exposing a major security flaw...

Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security

As large language models LLMs increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level cybersecurity threats, fundamentally different from prompt-based...

EX-NIDS: a Framework for Explainable Network Intrusion Detection Leveraging Large Language Models

This paper introduces eX-NIDS, a framework designed to enhance interpretability in flow-based Network Intrusion Detection Systems NIDS by leveraging Large Language Models LLMs. In our proposed framework, flows labelled as malicious by NIDS are initially processed through a module called the Promp...

Talking like a Phisher: LLM-Based Attacks on Voice Phishing Classifiers

Voice phishing vishing remains a persistent threat in cybersecurity, exploiting human trust through persuasive speech. While machine learning ML-based classifiers have shown promise in detecting malicious call transcripts, they remain vulnerable to adversarial manipulations that preserve semantic...

DREAM: Scalable Red Teaming for Text-To-Image Generative Systems Via Distribution Modeling

Despite the integration of safety alignment and external filters, text-to-image T2I generative models are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended exposure and potential misuse. Red teaming, which aims to...

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs

Large Language Models LLMs have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and investigate a new class of prompt-based attacks, termed...

PT-2025-30404 · Undefined · Undefined

CVE-2025-54356 Rejected reason https://t.co/wlhPkGwe6f Don't wait vulnerability scanning results: https://t.co/oh1APvMMnd...

Chaindesk 跨站脚本漏洞

Chaindesk is an AI chatbot for building and deploying private data-based chatbots from Chaindesk, France. A cross-site scripting vulnerability exists in Chaindesk version 2025-05-26 and earlier, which stems from a system prompt in the AI agent that can embed a malicious script payload, leading to...

git: Git does not sanitize URLs when asking for credentials interactively

A flaw was found in Git. This vulnerability occurs when Git requests credentials via a terminal prompt, for example, without the use of a credential helper. During this process, Git displays the host name for which the credentials are needed, but any URL-encoded parts are decoded and displayed...

TelegAI Cross Site Scripting

TelegAI, a web application for constructing and chatting with AI Characters, is vulnerable to persistent cross site scripting vulnerabilities in its chat component and character container component. An attacker can achieve arbitrary client-side script execution by crafting an AI Character with SV...

PromptArmor: Simple yet Effective Prompt Injection Defenses

Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specified task rather than the intended task provided by the user. In this paper, we...

Exploit for CVE-2025-51860

CVE-2025-51860 Vulnerability description TelegAI, a web...

Exploit for CVE-2025-51859

CVE-2025-51859 Vulnerability description Chaindesk, a w...

MAD-Spear: a Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems

Multi-agent debate MAD systems leverage collaborative interactions among large language models LLMs agents to improve reasoning capabilities. While recent studies have focused on increasing the accuracy and scalability of MAD systems, their security vulnerabilities have received limited attention...

Prompt Injection 2.0: Hybrid AI Threats

Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly disclosed to OpenAI. Over the last three years, these...

CVE-2025-27582

The Secure Password extension in One Identity Password Manager before 5.14.4 allows local privilege escalation. The issue arises from a flawed security hardening mechanism within the kiosk browser used to display the Password Self-Service site to end users. Specifically, the application attempts ...

PLA: Prompt Learning Attack against Text-To-Image Generative Models

Text-to-Image T2I models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work NSFW content. To investigate the vulnerability of T2I models, this paper delves into adversarial...

LLMalMorph: on the Feasibility of Generating Variant Malware Using Large-Language-Models

Large Language Models LLMs have transformed software development and automated code generation. Motivated by these advancements, this paper explores the feasibility of LLMs in modifying malware source code to generate variants. We introduce LLMalMorph, a semi-automated framework that leverages...

LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to Spearphishing

We introduce the framework of LLM-Stackelberg games, a class of sequential decision-making models that integrate large language models LLMs into strategic interactions between a leader and a follower. Departing from classical Stackelberg assumptions of complete information and rational agents, ou...