CVE-2024-32729

Improper Limitation of a Pathname to a Restricted Directory 'Path Traversal' vulnerability in QuantumCloud Conversational Forms for ChatBot allows Path Traversal. This issue affects Conversational Forms for ChatBot: from n/a through 1.1.8...

PT-2026-40007

A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. Applications using the affected advisor with user-controlled input may be susceptible to manipulation of model behavior across conversation turns...

A Synthetic Conversational Smishing Dataset for Social Engineering Detection

Smishing SMS phishing has become a serious cybersecurity threat, especially for elderly and cyber-unaware individuals, causing financial loss and undermining user trust. Although prior work has focused on detecting smishing at the level of individual messages, real-world attackers often rely on...

SentinelSphere: Integrating AI-Powered Real-Time Threat Detection with Cybersecurity Awareness Training

The field of cybersecurity is confronted with two interrelated challenges: a worldwide deficit of qualified practitioners and ongoing human-factor weaknesses that account for the bulk of security incidents. To tackle these issues, we present SentinelSphere, a platform driven by artificial...

CVE-2024-34380

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in QuantumCloud Conversational Forms for ChatBot allows Stored XSS.This issue affects Conversational Forms for ChatBot: from n/a through 1.2.0...

Cisco Finds Open-Weight AI Models Easy to Exploit in Long Chats

Cisco’s new research shows that open-weight AI models, while driving innovation, face serious security risks as multi-turn attacks, including conversational persistence, can bypass safeguards and expose data...

Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models

Large language models LLMs remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints gradually. These attacks target different harm categories like malware generation, harassment, or fraud through distinct conversational approaches...

RedTWIZ: Diverse LLM Red Teaming Via Adaptive Attack Planning

This paper presents the vision, scientific contributions, and technical details of RedTWIZ: an adaptive and diverse multi-turn red teaming framework, to audit the robustness of Large Language Models LLMs in AI-assisted software development. Our work is driven by three major research streams: 1...

EUVD-2025-30312

Malicious code in bioql PyPI...

EUVD-2024-34752

Malicious code in bioql PyPI...

MAL-2025-9587 Malicious code in @usaa-grp-conversational-search/ent-search-ui (npm)

The package @usaa-grp-conversational-search/ent-search-ui was found to contain malicious code...

Urania: Differentially Private Insights into AI Use

We introduce $Urania$, a novel framework for generating insights about LLM chatbot interactions with rigorous differential privacy DP guarantees. The framework employs a private clustering mechanism and innovative keyword extraction methods, including frequency-based, TF-IDF-based, and LLM-guided...

Introducing AI Attack Coverage in Exposure Command: Secure what traditional AppSec Tools miss

The rise of GenAI-powered applications – from internal copilots to customer-facing chatbots – is changing how businesses operate. While these tools drive innovation, they also introduce a fast moving, often invisible layer of risk. Most traditional AppSec tools were never built to handle the uniq...

CVE-2025-22813

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in QuantumCloud Conversational Forms for ChatBot conversational-forms allows Stored XSS.This issue affects Conversational Forms for ChatBot: from n/a through = 1.4.2...

CVE-2023-23981

Auth. admin+ Stored Cross-Site Scripting XSS vulnerability in QuantumCloud Conversational Forms for ChatBot plugin = 1.1.6 versions...

CVE-2025-32377 Rasa Pro Missing Authentication For Voice Connector APIs

Rasa Pro is a framework for building scalable, dynamic conversational AI assistants that integrate large language models LLMs. A vulnerability has been identified in Rasa Pro where voice connectors in Rasa Pro do not properly implement authentication even when a token is configured in the...

NVIDIA Riva riva_quickstart Access Control Error Vulnerability

NVIDIA Riva is a fully accelerated conversational AI application framework released by NVIDIA for building multimodal conversational AI services using end-to-end. An access control error vulnerability exists in NVIDIA Riva rivaquickstart, which can be exploited by an attacker to submit a special...

Google Rolls Out AI Scam Detection for Android to Combat Conversational Fraud

Google has announced the rollout of artificial intelligence AI-powered scam detection features to secure Android device users and their personal information. "These features specifically target conversational scams, which can often appear initially harmless before evolving into harmful situations...

CVE-2025-22813

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in QuantumCloud Conversational Forms for ChatBot conversational-forms allows Stored XSS.This issue affects Conversational Forms for ChatBot: from n/a through = 1.4.2...

WordPress plugin Conversational Forms for ChatBot 跨站脚本漏洞

WordPress and WordPress plugin are both products of the WordPress Foundation.WordPress is a blogging platform developed using the PHP language. The platform supports personal blog sites on PHP and MySQL servers.WordPress plugin is an application plugin. A cross-site scripting vulnerability exists...