8593 matches found
Trojans in Artificial Intelligence (TrojAI) Final Report
The Intelligence Advanced Research Projects Activity IARPA launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI Trojans. These AI trojans are malicious, hidden backdoors intentionally embedded within an AI model that can cause a...
Viral AI, Invisible Risks: What OpenClaw Reveals About Agentic Assistants
OpenClaw aka Clawdbot or Moltbot represents a new frontier in agentic AI: powerful, highly autonomous, and surprisingly easy to use. In this research, we examine how its capabilities compare to its predecessors’ and highlight the security risks inherent to the agentic AI paradigm...
CVE-2026-1927
The Greenshift – animation and page builder blocks plugin for WordPress is vulnerable to unauthorized access of data due to a missing capability check on the greenshiftapppassvalidation function in all versions up to, and including, 12.6. This makes it possible for authenticated attackers, with...
CVE-2026-25757
creationtimestamp| type| source ---|---|--- 2026-02-05 13:46:30+00:00| published-proof-of-concept| https://github.com/spree/spree/security/advisories/GHSA-p6pv-q7rc-g4h9 2026-03-06 20:09:04+00:00| seen|...
CVE-2026-1927
CVE-2026-1927 affects the Greenshift – animation and page builder blocks plugin for WordPress (versions up to and including 12.5.7). The root cause is a missing capability check in the greenshift_app_pass_validation() function, allowing authenticated attackers with Subscriber-level access and abo...
CVE-2026-1927 GreenShift - Animation and Page Builder Blocks <= 12.6 - Missing Authorization to Authenticated (Subscriber+) Information Disclosure of AI API Keys and Stored Cross-Site Scripting via custom_css
The Greenshift – animation and page builder blocks plugin for WordPress is vulnerable to unauthorized access of data due to a missing capability check on the greenshiftapppassvalidation function in all versions up to, and including, 12.6. This makes it possible for authenticated attackers, with...
CVE-2026-1927
The Greenshift – animation and page builder blocks plugin for WordPress is vulnerable to unauthorized access of data due to a missing capability check on the greenshiftapppassvalidation function in all versions up to, and including, 12.6. This makes it possible for authenticated attackers, with...
Exploit for CVE-2026-25253
OpenClaw Security Monitor Proactive security monitoring, thre...
Top AI Tools for Red Teaming in 2026
Red teaming has undergone a radical evolution. Modern organizations can no longer rely solely on human creativity or…...
Tanium Reputation 安全漏洞
Tanium Reputation is a threat intelligence integration engine developed by the American company Tanium. Tanium Reputation has a security vulnerability, which stems from improper access control practices...
Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent
Understanding TTPs Tactics, Techniques, and Procedures in malware binaries is essential for security analysis and threat intelligence, yet remains challenging in practice. Real-world malware binaries are typically stripped of symbols, contain large numbers of functions, and distribute malicious...
CERTFR-2026-CTI-001
creationtimestamp| type| source ---|---|--- 2026-02-04 13:00:41+00:00| seen| https://social.numerique.gouv.fr/users/certfr/statuses/116012485069158031...
Firefox is giving users the AI off switch
Some software providers have decided to lead by example and offer users a choice about the Artificial Intelligence AI features built into their products. The latest example is Mozilla, which now offers users a one-click option to disable generative AI features in the Firefox browser. Audiences ar...
Exposed AWS Credentials Lead to AI-Assisted Cloud Breach in 8 Minutes
Researchers recently tracked a high-speed cloud attack where an intruder gained full admin access in just eight minutes. Discover how AI automation and a simple storage error led to a major security breach...
Rapid7 vs. Hive Pro: A Head-to-Head Comparison
See how Rapid7 and Hive Pro compare in features, setup, pricing, and threat intelligence to help you choose the right threat exposure management platform. Threat intelligence and Business context are the secret sauces that transform vulnerability management from a frantic game of whack-a-mole int...
Session Handler Authentication Failure DoS
The vulnerability of the Session Handler component of the platform for creating and deploying work processes using AI agents is related to the lack of authentication for a critical function. Exploiting this vulnerability could allow an attacker to cause service failures...
Quarterly WordPress Threat Intelligence Report – Q4 2025
As the leader in WordPress security, Wordfence provides unparalleled security coverage that fully encompasses protection, active monitoring, detection, and response all built around our threat intelligence, demonstrating a strong commitment to security. Our mission is to ensure comprehensive...
Microsoft SDL: Evolving security practices for an AI-powered world
As AI reshapes the world, organizations encounter unprecedented risks, and security leaders take on new responsibilities. Microsoft’s Secure Development Lifecycle SDL is expanding to address AI-specific security concerns in addition to the traditional software security areas that it has...
Chrome Zero-Day Vulnerability: Are You Protected?
With billions of users, Google Chrome is more than just a browser; it’s a fundamental part of your organization's attack surface. It’s installed on nearly every endpoint, from the C-suite to the intern pool. This ubiquity is precisely what makes a Chrome zero-day vulnerability so uniquely...
ICYMI: Experts on Experts – Season One Roundup
In 2025, we launched Experts on Experts: Commanding Perspectives as a pilot video series designed to spotlight the ideas shaping cybersecurity, directly from the people driving them. Over five episodes, Rapid7 leaders shared short, candid conversations on topics like agentic AI, MDR ROI,...