Malicious Package

Overview agents-a365-runtime is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...

DeepSeek TUI: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files

Summary The taskcreate tool spawns durable sub-agents that inherit two insecure defaults: - allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue - autoapprove defaults to true taskmanager.rs:297: autoapprove: Sometrue When a user approves a taskcreate call which requires...

GHSA-72W5-PF8H-XFP4 DeepSeek TUI: task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files

Summary The taskcreate tool spawns durable sub-agents that inherit two insecure defaults: - allowshell defaults to true config.rs:1499: self.allowshell.unwraportrue - autoapprove defaults to true taskmanager.rs:297: autoapprove: Sometrue When a user approves a taskcreate call which requires...

Defense in depth for autonomous AI agents

Designing Secure Autonomous AI Agents with Defense in Depth AI agents are moving beyond assistance and into action. Instead of generating content, they invoke tools, modify data, trigger workflows, and operate across systems with increasing autonomy. This shift changes the security problem...

RHSA-2026:17083 Red Hat Security Advisory: fence-agents security update

Bulletin has no description...

PT-2026-41186

Name of the Vulnerable Software and Affected Versions CodeWhale versions prior to 0.8.26 Description The task create tool spawns durable sub-agents that inherit insecure default settings. Specifically, the allow shell variable defaults to true and the auto approve variable defaults to true. When ...

PT-2026-41166

Name of the Vulnerable Software and Affected Versions CodeWhale versions 0.3.0 through 0.8.22 Description The run tests tool executes cargo test in the workspace with ApprovalRequirement::Auto, allowing it to run without user approval. Because cargo test compiles and executes arbitrary...

Toward Securing AI Agents like Operating Systems

Autonomous agents based on large language models LLMs are rapidly emerging as a general-purpose technology, with recent systems such as OpenClaw extending their capabilities through broad tool use, third-party skills, and deeper integration into user environments. At the same time, these agentic...

FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing

Library fuzzing is essential for hardening the software supply chain, but adopting it at scale remains expensive. Practitioners still spend substantial effort on environment setup, struggle to generate harnesses that respect intricate API constraints, and lack reliable means to tell genuine libra...

WARD: Adversarially Robust Defense of Web Agents against Prompt Injections

Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedded in HTML content or visual interfaces. Existing guard models still suffer from limited generalization to unseen...

The vulnerability of the data collection tool for Azure Monitor Agents from virtual machines and physical servers arises from improper external management of file names or paths. This allows attackers to escalate their privileges.

The vulnerability of the data collection tool for Azure Monitor Agents, which are associated with virtual machines and physical servers, is related to incorrect external management of file names or paths. Exploiting this vulnerability can allow a malicious actor to increase their privileges...

Important: Red Hat Security Advisory: fence-agents security update

An update for fence-agents is now available for Red Hat Enterprise Linux 10.0 Extended Update Support. Red Hat Product Security has rated this update as having a security impact of Important. A Common Vulnerability Scoring System CVSS base score, which gives a detailed severity rating, is availab...

Microsoft's MDASH AI System Finds 16 Windows Flaws Fixed in Patch Tuesday

Microsoft has unveiled a new multi-model artificial intelligence AI-driven system called MDASH to facilitate vulnerability discovery and remediation at scale, adding that it's being tested by some customers as part of a limited private preview. MDASH, short for m ulti-mod el a gentic s canning h...

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents

Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full control of the target. However, existing LLM security benchmarks treat a crash as exploitation success. That single binary outcome collapses the hard...

RHEL 10 : fence-agents (RHSA-2026:17083)

The remote Redhat Enterprise Linux 10 host has packages installed that are affected by multiple vulnerabilities as referenced in the RHSA-2026:17083 advisory. The fence-agents packages provide a collection of scripts for handling remote power management for cluster devices. They allow failed or...

CVE-2026-8319

A weakness has been identified in aiwaves-cn agents up to e8c4e3c2d19739d3dff59e577d1c97090cc15f59. Affected by this issue is the function recallrelevantmemoriestoworkingmemory of the file core/cat/lookingglass/straycat.py of the component cheshirecatcore. This manipulation causes resource...

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions

Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and validation into one context, which increases the risk of...

VulnCheck KEV: CVE-2026-44338

PraisonAI is a multi-agent teams system. From version 2.5.6 to before version 4.6.34, PraisonAI ships a legacy Flask API server with authentication disabled by default. When that server is used, any caller that can reach it can access /agents and trigger the configured agents.yaml workflow throug...

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code...

MiracleLinux 8 : resource-agents-4.9.0-54.el8_10.33 (AXSA:2026-602:05)

The remote MiracleLinux 8 host has packages installed that are affected by a vulnerability as referenced in the AXSA:2026-602:05 advisory. pyasn1: pyasn1 Vulnerable to Denial of Service via Unbounded Recursion CVE-2026-30922 Tenable has extracted the preceding description block directly from the...