Amazon Is Using Specialized AI Agents for Deep Bug Hunting

Born out of an internal hackathon, Amazon’s Autonomous Threat Analysis system uses a variety of specialized AI agents to detect weaknesses and propose fixes to the company’s platforms...

Lack of Sufficient Guardrails Lead to Excessive Agency (LLM08) in Some LLM Applications

Overview Retell AI's API creates AI voice agents that have excessive permissions and functionality, as a result of insufficient amounts of guardrails. As a result, attackers can exploit this and conduct large scale social engineering, phishing, and misinformation campaigns. Description Retell AI...

LLMs As Firmware Experts: A Runtime-Grown Tree-Of-Agents Framework

Large Language Models LLMs and their agent systems have recently demonstrated strong potential in automating code reasoning and vulnerability detection. However, when applied to large-scale firmware, their performance degrades due to the binary nature of firmware, complex dependency structures, a...

AI as Cyberattacker

From Anthropic: In mid-September 2025, we detected suspicious activity that later investigation determined to be a highly sophisticated espionage campaign. The attackers used AI’s “agentic” capabilities to an unprecedented degree­--using AI not just as an advisor, but to execute the cyberattacks...

PT-2025-47728

The ELEX WordPress HelpDesk & Customer Ticketing System plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the 'eh crm remove agent' function in all versions up to, and including, 3.3.1. This makes it possible for authenticated attackers,...

Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...

Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming

Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests. However, existing approaches face trade-offs between generality and specialization, and practical deployments reveal challenges such as...

Incorrect Default Permissions

Overview Affected versions of this package are vulnerable to Incorrect Default Permissions via the Agents plugin process. An attacker can access information about when users have read channels by querying channel member objects. Remediation Upgrade...

EUVD-2025-198045

Mattermost allows other users to determine when users had read channels via channel member objects...

Mattermost allows other users to determine when users had read channels via channel member objects

Mattermost versions 10.11.x = 10.11.3, and 10.5.x = 10.5.11 fail to enforce access permissions on the Agents plugin which allows other users to determine when users had read channels via channel member objects...

GHSA-9HH7-6558-QFP2 Mattermost allows other users to determine when users had read channels via channel member objects

Mattermost versions 10.11.x = 10.11.3, and 10.5.x = 10.5.11 fail to enforce access permissions on the Agents plugin which allows other users to determine when users had read channels via channel member objects...

CVE-2025-53360

pluginsGLPI's Database Inventory Plugin "manages" the Teclib' inventory agents in order to perform an inventory of the databases present on the workstation. In versions prior to 1.0.3, any authenticated user could send requests to agents. This issue has been patched in version 1.0.3...

CVE-2025-55074

Mattermost versions 10.11.x = 10.11.3, 10.5.x = 10.5.11 fail to enforce access permissions on the Agents plugin which allows other users to determine when users had read channels via channel member objects...

EUVD-2025-198037

pluginsGLPI's Database Inventory Plugin "manages" the Teclib' inventory agents in order to perform an inventory of the databases present on the workstation. In versions prior to 1.0.3, any authenticated user could send requests to agents. This issue has been patched in version 1.0.3...

CVE-2025-53360

CVE-2025-53360 affects the pluginsGLPI Database Inventory Plugin for GLPI. Prior to version 1.0.3, any authenticated user could send requests to the Teclib’ inventory agents, effectively exposing/invoking inventory actions on workstation databases. The issue is mitigated by upgrading to version 1...

CVE-2025-53360 pluginsGLPI's Database Inventory Plugin allows any authenticated user to send agent requests

pluginsGLPI's Database Inventory Plugin "manages" the Teclib' inventory agents in order to perform an inventory of the databases present on the workstation. In versions prior to 1.0.3, any authenticated user could send requests to agents. This issue has been patched in version 1.0.3...

​​Ambient and autonomous security for the agentic era​​

Over the past year, I've had countless conversations with customers who are striving to unlock human ambition with AI. They are on their journey to become Frontier Firms, where humans and agents push the boundaries of innovation and create new possibilities, empowering humans to become limitless...

​​Ambient and autonomous security for the agentic era​​

Over the past year, I've had countless conversations with customers who are striving to unlock human ambition with AI. They are on their journey to become Frontier Firms, where humans and agents push the boundaries of innovation and create new possibilities, empowering humans to become limitless...

Agents built into your workflow: Get Security Copilot with Microsoft 365 E5

The cybersecurity landscape is at a historic inflection point. As cyberattackers wield AI to automate cyberattacks at extraordinary speed and scale, the challenge before us is not just to keep pace—but to leap ahead. There are over four million unfilled cybersecurity jobs, so depending solely on...

Agents built into your workflow: Get Security Copilot with Microsoft 365 E5

The cybersecurity landscape is at a historic inflection point. As cyberattackers wield AI to automate cyberattacks at extraordinary speed and scale, the challenge before us is not just to keep pace—but to leap ahead. There are over four million unfilled cybersecurity jobs, so depending solely on...