MAL-2026-4004 Malicious code in @antv/gi-assets-hugegraph (npm)

Part of the Mini Shai-Hulud supply chain attack campaign in which a threat actor compromised the npm account atool and published 631 malicious versions across 314 npm packages in an automated 22-minute burst. Each malicious version injects a preinstall hook that executes a 498KB obfuscated Bun...

MAL-2026-3864 Malicious code in @antv/coord (npm)

Part of the Mini Shai-Hulud supply chain attack campaign in which a threat actor compromised the npm account atool and published 631 malicious versions across 314 npm packages in an automated 22-minute burst. Each malicious version injects a preinstall hook that executes a 498KB obfuscated Bun...

MAL-2026-3964 Malicious code in @antv/g-web-components (npm)

Part of the Mini Shai-Hulud supply chain attack campaign in which a threat actor compromised the npm account atool and published 631 malicious versions across 314 npm packages in an automated 22-minute burst. Each malicious version injects a preinstall hook that executes a 498KB obfuscated Bun...

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data exfiltration, can cause irreversible harm. Existing defenses are...

The vulnerability of the WebSocket-server of the Gateway AI-agent OpenClaw (formerly known as ClawdBot or MoltBot) allows a perpetrator to execute arbitrary code.

The vulnerability of the WebSocket-server of the OpenClaw AI agent formerly known as ClawdBot or MoltBot is related to an uncontrolled element in the search path. Exploiting this vulnerability could allow a remote attacker to execute arbitrary code...

Cursor AI Agent Wipes PocketOS Database and Backups in 9 Seconds

PocketOS founder says Cursor AI agent deleted its production database in 9 seconds after misusing a root API token, exposing major Railway security flaws...

Anatomy of an Autonomous AI Agent Risk: How Qualys ETM Connects the Dots on OpenClaw

Executive Summary An unauthorized OpenClaw AI agent was detected disguised as a routine package on a Windows Server host. The situation escalated into a priority incident when Qualys ETM analyzed and correlated four distinct signals. While none of these signals alone warranted urgent action, the...

The vulnerability of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) in Windows operating systems arises from the failure to take measures to neutralize special elements. This vulnerability allows a perpetrator to execute arbitrary commands.

The vulnerability of the AI agent OpenClaw formerly known as ClawdBot or MoltBot in Windows operating systems is related to the failure to take measures to neutralize special elements. Exploiting this vulnerability allows a hacker to execute arbitrary commands...

The vulnerability of the collectConfigEnvVars() function in the OpenClaw AI agent (previously known as ClawdBot or MoltBot) allows a violator to execute arbitrary code.

The vulnerability of the collectConfigEnvVars function in the OpenClaw AI agent previously known as ClawdBot or MoltBot is related to errors in system configuration or settings. Exploiting this vulnerability allows a malicious actor to execute arbitrary code remotely...

CVE-2026-34724

Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1, a server-side template injection vulnerability which leads to RCE via AI Agent exists. Impact is limited to environments where an attacker can control or influence typeenrichmentdata typically high-privilege...

CVE-2026-34724 Zammad has a server-side template injection leading to RCE via AI Agent

Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1, a server-side template injection vulnerability which leads to RCE via AI Agent exists. Impact is limited to environments where an attacker can control or influence typeenrichmentdata typically high-privilege...

CVE-2026-34724 Zammad has a server-side template injection leading to RCE via AI Agent

Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1, a server-side template injection vulnerability which leads to RCE via AI Agent exists. Impact is limited to environments where an attacker can control or influence typeenrichmentdata typically high-privilege...

CVE-2026-34724: Improper Control of Generation of Code

Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1, a server-side template injection vulnerability which leads to RCE via AI Agent exists. Impact is limited to environments where an attacker can control or influence typeenrichmentdata typically high-privilege...

PT-2026-31421

Name of the Vulnerable Software and Affected Versions Zammad versions prior to 7.0.1 Description Zammad is a web-based open-source helpdesk/customer support system. A server-side template injection vulnerability exists via the AI Agent, potentially leading to Remote Code Execution RCE. The impact...

This Week in Spring - April 7th, 2026

Hi Spring fans! Welcome to another installment of This Week in Spring! It's April 7th, 2026, and I'm on the road! I started the journey for the amazing Voxxed Days Amsterdam show and am now winding my way through France. I visited Colmar, a beautiful city from which the animators on Disney's Beau...

The Kill Chain Is Obsolete When Your AI Agent Is the Threat

In September 2025, Anthropic disclosed that a state-sponsored threat actor used an AI coding agent to execute an autonomous cyber espionage campaign against 30 global targets. The AI handled 80-90% of tactical operations on its own, performing reconnaissance, writing exploit code, and attempting...

MAL-2026-2006 Malicious code in mangrove-sdk (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 d6714958f20775c2347e9c8b606d1de2e28ed29fe4b1a82261ca4fb966fc20fa During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...

MAL-2026-2004 Malicious code in flyio-token-client-efgh (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 2b09830263d8a35450ca657294a1725c441f2f7fe49cc7946e261e8f18401464 During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...

Exploit for CVE-2026-32746

autohack Autonomous security research framework. Inspired by...

A LINDDUN-Based Privacy Threat Modeling Framework for GenAI

As generative AI GenAI systems become increasingly prevalent across various technological stacks, the question of how such systems handle sensitive and personal data flows becomes increasingly important. Specifically, both the ability to harness and process large swaths of information as well as...