AI Can Forge Documents in Minutes – “Looks Right” Is No Longer Enough

Generative AI is making document fraud faster and harder to spot, pushing security teams to verify provenance, signatures and file integrity at intake securely...

SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing

Scanners meant to catch malicious add-on "skills" for AI coding agents can be fooled by a few simple changes that leave the malware working, according to a new study from researchers at the Hong Kong University of Science and Technology. Their strongest trick slipped past every scanner tested mor...

EUVD-2026-41611

A vulnerability was detected in SourceCodester CET Automated Grading System with AI Predictive Analytics 1.0. This issue affects some unknown processing. The manipulation results in session fixiation. The attack can be executed remotely. The attack requires a high level of complexity. The...

Chromium: CVE-2026-14151 Inappropriate implementation in AI

This CVE was assigned by Chrome. Microsoft Edge Chromium-based ingests Chromium, which addresses this vulnerability. Please see Google Chrome Releases for more information...

PT-2026-55582

Name of the Vulnerable Software and Affected Versions SourceCodester CET Automated Grading System with AI Predictive Analytics version 1.0 Description An authorization bypass exists in the POST Handler component. Remote exploitation is possible by manipulating the ID variable within the...

VMware Licensing Changes and Their Impact on Infrastructure Modernization

Explore how VMware licensing changes are influencing infrastructure modernization, cloud strategy, and AI readiness, and what enterprises should evaluate next...

Identity Lifecycle Management Wasn't Built for AI Agents 

Identity lifecycle management was architected around a person with an employment record, a manager, and a departure date. AI agents have none of those. As autonomous principals proliferate across enterprise environments, the governance model built for humans develops structural blind spots that...

AI Agent Exploits Langflow RCE to Automate Database Ransomware Attack

Security firm Sysdig says it has found what it believes is the first ransomware attack run from start to finish by an AI agent. Its Threat Research Team calls the operator JADEPUFFER and says a large language model handled the whole job: breaking in, stealing credentials, moving deeper into the...

Important: Red Hat Security Advisory: Red Hat AI Base Images 3.0.2 (tpu)

Red Hat AI Base Images 3.0.2 tpu is now available. Red Hat® AI Base Images...

Important: Red Hat Security Advisory: Red Hat AI Base Images 3.2.2 (TPU)

Red Hat AI Base Images 3.2.2 TPU is now available. Red Hat® AI Base Images...

Important: Red Hat Security Advisory: Red Hat AI Base Images 3.3.2 (CUDA 12.9)

Red Hat AI Base Images 3.3.2 CUDA 12.9 is now available. Red Hat® AI Base Images...

bak-exploitarium

https://discord.gg/WytKH65ZR join up for research, help, documen...

A Bootiful Podcast: Sébastien Deleuze on the latest-and-greatest in Spring AI and Spring Framework

Hi Spring fans! In this installment we talk to the legendary Spring AI and Spring Framework contributor Sébastien Deleuze about the latest-and-greatest in AI, Kotlin, the framework, and more...

The Cost of Non-Compliance: Why AI Governance Is the New Enterprise Imperative

AI governance helps enterprises control tool use, reduce compliance risk, protect customer data, and avoid fines as teams adopt AI faster than policy...

DRUPAL-CONTRIB-2026-067

This module enables you to test and run AI-driven workflows interactively through a chat interface. The module doesn't sufficiently enforce permissions on certain endpoints. Attackers may be able to trigger workflow execution incurring LLM spend and tool side effects or send messages into other...

DRUPAL-CONTRIB-2026-065

The Canvas AI submodule allows you to upload image files via a custom API to use within the AI web chat. These file uploads are insufficiently validated before being written to Drupal's temporary directory. In some cases, this may lead to cross-site scripting XSS...

CVE-2026-12408

The Slim SEO – A Fast & Automated SEO Plugin For WordPress plugin for WordPress is vulnerable to Unauthorized Private Content Disclosure in all versions up to, and including, 4.9.8 via the /wp-json/slim-seo/meta-tags/ai REST API endpoint. This is due to the endpoint's permissioncallback performin...

CVE-2026-12408

The CVE-2026-12408 entry concerns the WordPress plugin Slim SEO (versions up to and including 4.9.8). The vulnerability arises from the REST endpoint /wp-json/slim-seo/meta-tags/ai: the permission_callback only checks a top-level edit_posts capability and does not verify that the requester can re...

CVE-2026-12408

The Slim SEO – A Fast & Automated SEO Plugin For WordPress plugin for WordPress is vulnerable to Unauthorized Private Content Disclosure in all versions up to, and including, 4.9.8 via the /wp-json/slim-seo/meta-tags/ai REST API endpoint. This is due to the endpoint's permissioncallback performin...

EUVD-2026-40838

Inappropriate implementation in AI in Google Chrome prior to 150.0.7871.47 allowed a remote attacker who had compromised the renderer process to potentially perform a sandbox escape via a crafted HTML page. Chromium security severity: Low...