The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey

AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex security challenges fundamentally different from those in...

PT-2026-24720

CVE-2026-30741 – OpenClaw Agent Platform Remote Code Execution is severe risk to AI automation pipelines and DPI Full analysis: https://t.co/LWSf0pscCB CyberSecurity AISecurity PromptInjection RemoteCodeExecution ThreatIntelligence LLMSecurity AgentSecurity DevSecOps...

PT-2026-24754

A problem with a protection mechanism in the Palo Alto Networks Cortex XDR agent on macOS allows a local administrator to disable the agent. This issue could be leveraged by malware to perform malicious activity without detection...

Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles toward suboptimal routes and increase congestion. To addres...

Palo Alto Networks Cortex XDR Broker VM 安全漏洞

Palo Alto Networks Cortex XDR Broker VM is a secure virtual machine developed by Palo Alto Networks. It integrates with Cortex XDR and can bridge networks with Cortex XDR. There is a security vulnerability in the Palo Alto Networks Cortex XDR agent. This vulnerability stems from issues with the...

CVE-2026-30741

OpenClaw Agent Platform up to v2026.2.6 is affected by a remote code execution (RCE) via a Request-Side prompt injection attack. The root cause is a lack of integrity validation for upstream API requests, which can cause high‑severity command execution in downstream components (e.g., MCP tools) w...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

CVE-2026-30741

A remote code execution RCE vulnerability in OpenClaw Agent Platform v2026.2.6 allows attackers to execute arbitrary code via a Request-Side prompt injection attack...

VulnCheck KEV: CVE-2025-62593

Ray is an AI compute engine. Prior to version 2.52.0, developers working with Ray as a development tool can be exploited via a critical RCE vulnerability exploitable via Firefox and Safari. This vulnerability is due to an insufficient guard against browser-based attacks, as the current defense us...

CVE-2026-31829 Flowise affected by Server-Side Request Forgery (SSRF) in HTTP Node Leading to Internal Network Access

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.0.13, Flowise exposes an HTTP Node in AgentFlow and Chatflow that performs server-side HTTP requests using user-controlled URLs. By default, there are no restrictions on target hosts, including...

EUVD-2026-10688

Authentication bypass using an alternate path or channel in Azure Windows Virtual Machine Agent allows an authorized attacker to elevate privileges locally...

EUVD-2025-208492

An Improper Limitation of a Pathname to a Restricted Directory 'Path Traversal' vulnerability CWE-22 vulnerability in Fortinet FortiSOAR Agent Communication Bridge 1.1.0, FortiSOAR Agent Communication Bridge 1.0 all versions may allow an unauthenticated attacker to read files accessible to the...

CVE-2026-26117

Authentication bypass using an alternate path or channel in Azure Windows Virtual Machine Agent allows an authorized attacker to elevate privileges locally...

CVE-2025-54659

An Improper Limitation of a Pathname to a Restricted Directory 'Path Traversal' vulnerability CWE-22 vulnerability in Fortinet FortiSOAR Agent Communication Bridge 1.1.0, FortiSOAR Agent Communication Bridge 1.0 all versions may allow an unauthenticated attacker to read files accessible to the...

CVE-2026-30969 Coral Server has insufficient agent authentication in session communication channels

Coral Server is open collaboration infrastructure that enables communication, coordination, trust and payments for The Internet of Agents. Prior to 1.1.0, Coral Server did not enforce strong authentication between agents and the server within an active session. This could allow an attacker who...

CVE-2026-30969

CVE-2026-30969 affects Coral Server prior to version 1.1.0, where active-session authentication between agents and the server was not enforced. An attacker who could obtain or predict a session identifier could impersonate an agent or join an existing session. The issue is resolved in version 1.1...

CVE-2026-30968 Coral Server has insufficient validation of agent identity for SSE connections

Coral Server is open collaboration infrastructure that enables communication, coordination, trust and payments for The Internet of Agents. Prior to 1.1.0, the SSE endpoint /sse/v1/... in Coral Server did not strongly validate that a connecting agent was a legitimate participant in the session. Th...

CVE-2026-30968 Coral Server has insufficient validation of agent identity for SSE connections

Coral Server is open collaboration infrastructure that enables communication, coordination, trust and payments for The Internet of Agents. Prior to 1.1.0, the SSE endpoint /sse/v1/... in Coral Server did not strongly validate that a connecting agent was a legitimate participant in the session. Th...

CVE-2026-30968

Summary: Coral Server’s SSE endpoint (/sse/v1/...) did not strongly validate that a connecting agent was a legitimate session participant before version 1.1.0, potentially allowing unauthorized message injection or observation. Affected versions: prior to 1.1.0. Impact: stated as possible confide...