Researchers Uncover GPT-5 Jailbreak and Zero-Click AI Agent Attacks Exposing Cloud and IoT Systems

Cybersecurity researchers have uncovered a jailbreak technique to bypass ethical guardrails erected by OpenAI in its latest large language model LLM GPT-5 and produce illicit instructions. Generative artificial intelligence AI security platform NeuralTrust said it combined a known technique calle...

Exploit for Use After Free in Microsoft

🛑 CVE-2025-21298 – Critical Zero-Click RCE in Microsoft Window...

Cross-site Scripting (XSS)

Cadwyn is vulnerable to Reflected Cross-Site Scripting XSS. The vulnerability is due to improper handling of the version parameter in the /docs endpoint, which allows an attacker to execute arbitrary JavaScript in a user's session via a one-click attack...

PYSEC-2025-71

Cadwyn creates production-ready community-driven modern Stripe-like API versioning in FastAPI. In versions before 5.4.3, the version parameter of the "/docs" endpoint is vulnerable to a Reflected XSS Cross-Site Scripting attack. This XSS would notably allow an attacker to execute JavaScript code ...

Preventing Zero-Click AI Threats: Insights from EchoLeak

A zero-click exploit called EchoLeak reveals how AI assistants like Microsoft 365 Copilot can be manipulated to leak sensitive data without user interaction. This entry breaks down how the attack works, why it matters, and what defenses are available to proactively mitigate this emerging AI-nativ...

WordPress WP-Click-Tracker Plugin <= 0.7.3 - Cross Site Scripting (XSS) Vulnerability

Cross Site Scripting XSS Vulnerability discovered by Nguyen Xuan Chien in WordPress Plugin WP-Click-Tracker versions = 0.7.3...

Can Large Language Models Improve Phishing Defense? A Large-Scale Controlled Experiment on Warning Dialogue Explanations

Phishing has become a prominent risk in modern cybersecurity, often used to bypass technological defences by exploiting predictable human behaviour. Warning dialogues are a standard mitigation measure, but the lack of explanatory clarity and static content limits their effectiveness. In this pape...

CVE-2025-28983 WordPress Click & Pledge Connect plugin <= 25.04010101-WP6.8 - Privilege Escalation via SQL Injection vulnerability

Improper Neutralization of Special Elements used in an SQL Command 'SQL Injection' vulnerability in ClickandPledge Click & Pledge Connect allows Privilege Escalation. This issue affects Click & Pledge Connect: from 25.04010101 through WP6.8...

CVE-2025-28983 WordPress Click & Pledge Connect plugin <= 25.04010101-WP6.8 - Privilege Escalation via SQL Injection vulnerability

Improper Neutralization of Special Elements used in an SQL Command 'SQL Injection' vulnerability in ClickandPledge Click & Pledge Connect allows Privilege Escalation. This issue affects Click & Pledge Connect: from 25.04010101 through WP6.8...

CVE-2025-28983

CVE-2025-28983 describes an SQL Injection in Click & Pledge Connect for WordPress plugin versions 25.04010101 through WP6.8 that enables privilege escalation. The CVE is rated with a high impact (CVSS 3.1, base 9.8) and network attack vector with no user interaction required. Connected sources co...

WordPress plugin Click & Pledge Connect SQL注入漏洞

WordPress and WordPress plugin are both products of the WordPress Foundation.WordPress is a blogging platform developed using the PHP language. The platform supports setting up personal blog sites on servers with PHP and MySQL.WordPress plugin is an application plugin. A SQL injection vulnerabili...

PT-2025-27905 · Click & Pledge · Click & Pledge Connect

Name of the Vulnerable Software and Affected Versions: Click & Pledge Connect versions 25.04010101 through WP6.8 Description: The issue is related to an SQL Injection vulnerability due to improper neutralization of special elements used in an SQL command. This allows for privilege escalation...

CVE-2025-34072 Anthropic Slack MCP Server Data Exfiltration via Link Unfurling

A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol MCP Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing attacker-crafted hyperlinks embeddin...

CVE-2025-34072 Anthropic Slack MCP Server Data Exfiltration via Link Unfurling

A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol MCP Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing attacker-crafted hyperlinks embeddin...

PT-2025-27630 · Anthropic · Slack Model Context Protocol (Mcp) Server

Name of the Vulnerable Software and Affected Versions: Anthropic’s Slack Model Context Protocol MCP Server affected versions not specified Description: A data exfiltration issue exists in the deprecated Slack Model Context Protocol MCP Server via automatic link unfurling. When an AI agent using t...

CVE-2025-36027

IBM Datacap 9.1.7, 9.1.8, and 9.1.9 could allow a remote attacker to hijack the clicking action of the victim. By persuading a victim to visit a malicious Web site, a remote attacker could exploit this vulnerability to hijack the victim's click actions and possibly launch further attacks against...

Security Bulletin: Multiple Vulnerabilities in IBM Datacap

Summary Multiple vulnerabilities were addressed in IBM Datacap version 9.1.9 Interim Fix 007 Vulnerability Details CVEID:CVE-2025-36027 DESCRIPTION: IBM Datacap could allow a remote attacker to hijack the clicking action of the victim. By persuading a victim to visit a malicious Web site, a remot...

CVE-2025-36027

IBM Datacap 9.1.7, 9.1.8, and 9.1.9 could allow a remote attacker to hijack the clicking action of the victim. By persuading a victim to visit a malicious Web site, a remote attacker could exploit this vulnerability to hijack the victim's click actions and possibly launch further attacks against...

CVE-2024-39730

IBM Datacap Navigator 9.1.7, 9.1.8, and 9.1.9 could allow a remote attacker to hijack the clicking action of the victim. By persuading a victim to visit a malicious Web site, a remote attacker could exploit this vulnerability to hijack the victim's click actions and possibly launch further attack...

CVE-2024-39730

IBM Datacap Navigator 9.1.7, 9.1.8, and 9.1.9 could allow a remote attacker to hijack the clicking action of the victim. By persuading a victim to visit a malicious Web site, a remote attacker could exploit this vulnerability to hijack the victim's click actions and possibly launch further attack...