2092 matches found
EUVD-2026-53879
Unauthenticated PHP Object Injection in AI ANN = 1.29.0 versions...
CVE-2026-65581 WordPress AI ANN theme <= 1.29.0 - PHP Object Injection vulnerability
Unauthenticated PHP Object Injection in AI ANN = 1.29.0 versions...
CVE-2026-65545
Unauthenticated Cross Site Scripting XSS in AI Engine = 3.6.8 versions...
Cloud Threat Highlights: H1 2026
Cloud and AI threat activity tracked by Wiz Research and CIRT, January through June 2026...
MAL-2026-13411 Malicious code in @addai/node (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6ca685518d56ea513609a2dfcd845bb14d94c3faaf58645553c688ca59817921 The package installs a background daemon dist/session-runner.js that pairs the host to a remote +Ai account and polls a hardcoded Supabase backend at...
Malicious code in @addai/node (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6ca685518d56ea513609a2dfcd845bb14d94c3faaf58645553c688ca59817921 The package installs a background daemon dist/session-runner.js that pairs the host to a remote +Ai account and polls a hardcoded Supabase backend at...
With Val Kilmer’s AI Twin, Is Gen AI Forcing Hollywood to the Edge?
...
exploitarium
Statement This repo was incomplete when published. In regar...
OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree
At the Black Hat security conference, the AI giant revealed new details about how its agents went rogue, hacked several other companies—and did it all right under the company’s nose...
The Vulnerability with No CVE: Managing Persistent Gaps between Mandate and Authority in AI Coding Agents
Existing guidance identifies excessive agency, excessive permission, weak task-bound authorization, and inadequate agent controls as important risks. Control frameworks also describe capabilities for constraining, authorizing, observing, validating, and responding to agent activity. Yet security...
RHEL 9 : RHEL AI 3.3 RPM runtime CVE fix - aom (Important) (RHSA-2026:51100)
The remote Redhat Enterprise Linux 9 host has packages installed that are affected by multiple vulnerabilities as referenced in the RHSA-2026:51100 advisory. RPM packages are internal build artifacts and not supported on their own. They are only supported as part of the Red Hat AI application...
RHEL 9 : RHEL AI 3.4 RPM runtime CVE fix - aom (Important) (RHSA-2026:51146)
The remote Redhat Enterprise Linux 9 host has packages installed that are affected by multiple vulnerabilities as referenced in the RHSA-2026:51146 advisory. RPM packages are internal build artifacts and not supported on their own. They are only supported as part of the Red Hat AI application...
The Most Dangerous AI Hacking Techniques Still Have Humans in the Loop
Security researcher James Kettle tried to push the limit of AI’s hacking abilities—and discovered how effective it can be when combined with human expertise...
Meta Ran Ads That Contained AI-Generated Child Sexual Abuse Imagery
More than 50 offending image and video ads were published across Facebook, Instagram, Messenger, or Threads, according to Meta’s ad library data. Some ran as recently as this week...
Agentic AI Security: The Chatbot Era Is Already Over
This is Post 1 of a three-part series. Continue toPost 2: Generative AI Security: Why AI Needs a New Kind of Security, then continue to Post 3: OWASP LLM Top 10: What Comes Next – Agentic & MCP. There is a diagram most security teams still carry in their heads when they think about AI. A user tal...
Incident Report: Unsanctioned Agent Behaviour during Cyber Testing
During a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. The AI Security Institute is disclosing what they found, what it means, and the actions now underway...
OK, Well, Rogue AI Agents Are Hacking Again
Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior...
EUVD-2026-52925
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.9.6 until 0.11.0, the built-in knowledge search path in backend/openwebui/tools/knowledgefs.py and backend/openwebui/tools/builtin.py let a chat participant choose a pattern used to grep knowledge files...
Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOps
The calculus of cybersecurity has changed. AI is reshaping how organizations build, deploy, operate, and defend digital systems. AI-powered development tools, agents, and autonomous workflows are accelerating innovation but they are also introducing new attack surfaces, new trust boundaries, and...