CVE-2026-19889 Server-Side Request Forgery (SSRF) in GitLab AI Gateway

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.9.0 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect model requests to an...

EUVD-2026-67087

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.9.0 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect model requests to an...

Security Bulletin: Multiple vulnerabilities in IBM MQ Agent images

Summary Multiple vulnerabilities were addressed in IBM MQ Agent images Vulnerability Details CVEID:CVE-2026-62995 DESCRIPTION: joserfc is a Python library that provides an implementation of several JSON Object Signing and Encryption JOSE standards. in versions 1.7.1 and prior, joserfc accepts JWT...

​​​​​​What’s new in Microsoft Security: August 2026

As organizations incorporate AI agents into more processes across business and operations, security teams can benefit from greater visibility and new purpose-built tools that help manage, secure, and govern AI. This month’s updates provide new capabilities to help organizations gain insights into...

OpenClaw went viral. Meet the maintainers building and securing it.

What began as a personal experiment quickly became a global open source project with extraordinary momentum. OpenClaw is a personal AI assistant that runs on users' devices and connects with the messaging channels they already use. Started by Peter Steinberger as a weekend project in November 202...

From Concept to Context Engine: How Wiz Built AI-Powered Data Discovery

Inside the multi-agent pipeline and feedback loops that turned a bucket scanner into a context engine...

SkillSpector v2.10.0

SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...

ai.fastllm:agent-bridge_3 (>=0.3.0, <=0.5.6), ai.fastllm:agent-cli_3 (>=0.3.0, <=0.5.6) +1245 more potentially affected by CVE-2026-47892 via org.springframework:spring-webflux (>=7.0.0, <=7.0.8)

org.springframework:spring-webflux MAVEN version =7.0.0, =0.3.0, =0.3.0, =0.3.0, =0.3.0, =0.3.0, =1.0.0-beta.1, =0.1.0, =0.1.0, =4.13.5, =4.5.0, =4.5.0, =4.5.0, =4.5.0, =4.7.0-beta.3, =1.5.0, =1.7.0 and more Source cves: CVE-2026-47892 Source advisory: GHSA-9QF2-26P9-2Q2Q...

PT-2026-82769

Wazuh is an open-source security platform providing unified XDR and SIEM protection for endpoints and cloud workloads. In versions 4.0.0 through 4.14.6, a malicious or man-in-the-middle enrollment manager can crash a Wazuh agent during enrollment by returning a malformed key response with fewer...

RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution

LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater risks than unsafe text generation alone. Existing automatic red-teaming methods often rely on fixed attacks, while recent...

The Guard That Cried Wolf: How Scary Words Make Agent Guardrails Refuse Legitimate Actions

Agent guardrails are checks that approve or refuse each action before an LLM executes it. Sometimes they refuse requests that are genuinely safe. This over-safety blocks deployment when a guardrail refuses an authorized task. Evaluating over-safety is hard: at the boundary an authorized action...

Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction

Agent skills bundle instructions, reference data, and executable helpers that let a general agent perform specialized tasks. Hosted providers can keep these files secret while selling access to task results, making the skill itself a valuable target. Existing disclosure defenses can block request...

ContextLeak: Exfiltrating LLM Agent Context Via Malicious Tools

Exfiltrating an LLM agent's runtime context -- such as the user prompt, execution trajectory, and tool list -- poses severe security and privacy risks to users. Such attacks can be carried out via malicious tools and typically require three conditions: 1 the agent selects the malicious tool for...

When Context Gets Root: Privilege Escalation in LLM Harnesses

Instruction hierarchy is a model-side defense that assigns instructions different levels of privilege according to their sources. These levels constrain which content may direct model behavior. During agent execution, however, agent harnesses construct context for each model invocation. This...

Exploit for CVE-2026-75898

CVE-2026-75898 — RAGFlow Invoke component SSRF Server-Side Re...

CVE-2026-48786

Fleet is an open-source device management platform built on osquery. In versions prior to 4.87.0, the target search endpoint POST /api/latest/fleet/targets returned unmasked team enroll secrets and full team configuration, including credential-bearing agent options, to low-privilege observer-clas...

CVE-2026-48786

Fleet is an open-source device management platform built on osquery. In versions prior to 4.87.0, the target search endpoint POST /api/latest/fleet/targets returned unmasked team enroll secrets and full team configuration, including credential-bearing agent options, to low-privilege observer-clas...

zen-ai

Zen Open-source offensive security agents. Autonomous pen...

When an AI Agent Turned Attacker: What Qualys Sees Across Every Phase of the Hugging Face Kubernetes Intrusion

A phase-by-phase detection mapping of the first publicly documented autonomous agent intrusion against production infrastructure — including the phases where no product in our category sees anything at all. Executive Summary On July 9, 2026, an autonomous AI agent running inside an OpenAI...

CVE-2026-18252

GitLab has remediated an issue in GitLab EE affecting all versions from 18.9 before 19.1.7, 19.2 before 19.2.5, and 19.3 before 19.3.1 that, under certain conditions, an authenticated user with developer-role permissions could have executed arbitrary commands in a CI context, due to the Claude...