Exploit for CVE-2025-11749

CVE-2025-11749 AI Engine = 3.1.3 - Unauthenticated Sensiti...

CVE-2025-63638

Sourcecodester AI-Powered To-Do List App v1.0 is vulnerable to Cross-Site Scripting XSS in the "Task Title" and "Description Optional" fields when creating a Task, allowing an attacker to inject arbitrary potentially malicious HTML/JavaScript code that executes in the victim's browser upon clicki...

Faking Receipts with AI

Over the past few decades, it's become easier and easier to create fake receipts. Decades ago, it required special paper and printers--I remember a company in the UK advertising its services to people trying to cover up their affairs. Then, receipts became computerized, and faking them required...

Vibe-Coded Malicious VS Code Extension Found with Built-In Ransomware Capabilities

Cybersecurity researchers have flagged a malicious Visual Studio Code VS Code extension with basic ransomware capabilities that appears to be created with the help of artificial intelligence – in other words, vibe-coded. Secure Annex researcher John Tuckner, who flagged the extension "susvsex,"...

GHSA-RWVC-J5JR-MGVH Vercel’s AI SDK's filetype whitelists can be bypassed when uploading files

A vulnerability in Vercel’s AI SDK has been fixed in versions 5.0.52, 5.1.0-beta.9, and 6.0.0-beta. This issue may have allowed users to bypass filetype whitelists when uploading files. All users are encouraged to upgrade...

CVE-2025-48985

A vulnerability in Vercel’s AI SDK has been fixed in versions 5.0.52, 5.1.0-beta.9, and 6.0.0-beta. This issue may have allowed users to bypass filetype whitelists when uploading files. All users are encouraged to upgrade. More details:...

CVE-2025-48985

The CVE-2025-48985 vulnerability affects Vercel’s AI SDK, with fixes in versions 5.0.52, 5.1.0-beta.9, and 6.0.0-beta. The issue is an input-validation bypass that could allow bypassing filetype whitelists during file uploads. Connected sources confirm remediation via upgrading the AI SDK. Impact...

CVE-2025-63639

The chat feature in the application Sourcecodester FAQ Bot with AI Assistant v1.0 is vulnerable to Cross-Site Scripting XSS due to improper handling of user-supplied input. An attacker can inject malicious HTML or JavaScript into chat messages, which executes in the browser of any user viewing th...

CVE-2025-63639

The CVE-2025-63639 entry describes an XSS vulnerability in Sourcecodester FAQ Bot with AI Assistant v1.0, specifically in the chat feature where user input is not properly sanitized. Affected component: chat/messages handling in the FAQ Bot. Root cause: improper handling of user-supplied input le...

CVE-2025-62039

Summary (CVE-2025-62039) Insertion of Sensitive Information Into Sent Data affects the WordPress plugin “AI ChatBot with ChatGPT and Content Generator by AYS” (versions up to 2.6.6). The issue allows retrieval of embedded sensitive data from sent data, as described by multiple sources. CVSS v3.1 ...

AI Explainer: What Is Model Context Protocol?

...

Do robots dream of secure networking? Teaching cybersecurity to AI systems

This blog explores how to equip autonomous AI agents with cybersecurity knowledge, enabling them to make informed decisions about internet safety, such as identifying trustworthy links and websites. It demonstrates a proof of concept using LangChain and OpenAI, integrated with the Cisco Umbrella...

Automated and Explainable Denial of Service Analysis for AI-Driven Intrusion Detection Systems

With the increasing frequency and sophistication of Distributed Denial of Service DDoS attacks, it has become critical to develop more efficient and interpretable detection methods. Traditional detection systems often struggle with scalability and transparency, hindering real-time response and...

CVE-2025-12695

The overly permissive sandbox configuration in DSPy allows attackers to steal sensitive files in cases when users build an AI agent which consumes user input and uses the “PythonInterpreter” class...

​​Learn what generative AI can do for your security operations center

The busier security teams get, the harder it can be to understand the full impact of false positives, queue clutter, tool fragmentation, and more. But what is clear—it all adds up to increased fatigue and an increased potential to miss the cyberthreats that matter most. To help security teams...

Wizdom 2025 Product Announcements: Extending the Cloud Operating Model

At Wizdom 2025, we’re unveiling two new AI agents alongside new product innovations that deepen and extend the graph across SaaS, workloads, AI infrastructure, and external exposures. Together, these advances enable teams to secure everything they build and run in the cloud and beyond...

When AI Becomes the Heart of Security: Powering a Future You Can Trust

Helping teams see clearly, decide wisely, and move safely...

AI-Powered Wiz: From Agents to Everyday Intelligence

How Wiz AI Agents and Integrations Meet You Where You Work...

Securing AI Agents with Wiz AI-SPM

How Wiz brings visibility, context, and continuous defense to the new era of intelligent automation...

GHSA-VVW2-H478-XWR3 DSPy does not properly restrict file reads

The overly permissive sandbox configuration in DSPy allows attackers to steal sensitive files in cases when users build an AI agent which consumes user input and uses the “PythonInterpreter” class...