Dialogue App 安全漏洞

Dialogue App is an artificial intelligence dialogue application developed by Dialogue Company. Versions of Dialogue App 4.3.2 and earlier contained security vulnerabilities, which were caused by the use of a hardcoded encryption key for the parameter SEGMENTWRITEKEY...

Red Hat Ansible Automation Platform 2 安全漏洞

Red Hat Ansible Automation Platform 2 is software developed by Red Hat Inc. It is used for building, deploying, and managing automation processes. There is a security vulnerability in Red Hat Ansible Automation Platform 2. This vulnerability stems from the dialogue endpoints that handle AI chat...

EUVD-2006-2155

Malware in sbrugna...

EUVD-2014-7194

Malware in sbrugna...

EUVD-2002-0714

Malware in sbrugna...

EUVD-2024-31964

Malicious code in bioql PyPI...

EUVD-2022-51546

Malicious code in bioql PyPI...

Malicious Package

Overview moodle-core-notification-dialogue is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and...

MAL-2025-42152 Malicious code in moodle-core-notification-dialogue (npm)

The package moodle-core-notification-dialogue was found to contain malicious code. --- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 0744d3959a7e6cf0b70432a2b72939c580eb705bf7e14a8f4569ae3e0f571164 Any computer that has this package installed or running should be...

Malicious code in moodle-core-notification-dialogue (npm)

The package moodle-core-notification-dialogue was found to contain malicious code. --- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 0744d3959a7e6cf0b70432a2b72939c580eb705bf7e14a8f4569ae3e0f571164 Any computer that has this package installed or running should be...

Tricking LLM-Based NPCs into Spilling Secrets

Large Language Models LLMs are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs to reveal hidden background secrets that are meant to remai...

Malicious code in new-al-bum-av-ailable-24973-black-dialogue-hdrb2-ckuphe (npm)

The package new-al-bum-av-ailable-24973-black-dialogue-hdrb2-ckuphe was found to contain malicious code...

Generative AI for Critical Infrastructure in Smart Grids: a Unified Framework for Synthetic Data Generation and Anomaly Detection

In digital substations, security events pose significant challenges to the sustained operation of power systems. To mitigate these challenges, the implementation of robust defense strategies is critically important. A thorough process of anomaly identification and detection in information and...

ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls

Large Language Models LLMs have demonstrated impressive fluency and reasoning capabilities, but their potential for misuse has raised growing concern. In this paper, we present ScamAgent, an autonomous multi-turn agent built on top of LLMs, capable of generating highly realistic scam call scripts...

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs

Large Language Models LLMs for code generation i.e., Code LLMs have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating vulnerable or even malicious code under adversarial settings...

CVE-2020-10262

An issue was discovered on XIAOMI XIAOAI speaker Pro LX06 1.58.10. Attackers can activate the failsafe mode during the boot process, and use the miconsole command cascaded by the SN code shown on the product to get the root shell password, and then the attacker can i read Wi-Fi SSID or password, ...

GSDFuse: Capturing Cognitive Inconsistencies from Multi-Dimensional Weak Signals in Social Media Steganalysis

The ubiquity of social media platforms facilitates malicious linguistic steganography, posing significant security risks. Steganalysis is profoundly hindered by the challenge of identifying subtle cognitive inconsistencies arising from textual fragmentation and complex dialogue structures, and th...

Building Trustworthy Multimodal AI: a Review of Fairness, Transparency, and Ethics in Vision-Language Tasks

Objective: This review explores the trustworthiness of multimodal artificial intelligence AI systems, specifically focusing on vision-language tasks. It addresses critical challenges related to fairness, transparency, and ethical implications in these systems, providing a comparative analysis of...

CVE-2024-3375

Incorrect Permission Assignment for Critical Resource vulnerability in Havelsan Inc. Dialogue allows Accessing Functionality Not Properly Constrained by ACLs. This issue affects Dialogue: from v1.83 before v1.83.1 or v1.84...

CVE-2024-48918 Lack of Input Validation in RDS Light - Potential for Injection Attacks and Memory Tampering

RDS Light is a simplified version of the Reflective Dialogue System RDS, a self-reflecting AI framework. Versions prior to 1.1.0 contain a vulnerability that involves a lack of input validation within the RDS AI framework, specifically within the user input handling code in the main module main.p...