AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents

Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain confined to a single interface; instead, they can propagat...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.28 contained security vulnerabilities. These vulnerabilities stemmed from an execution approval vulnerability in the exec-approvals-allowlist.ts file, which allowed the...

CVE-2026-6741 LatePoint <= 5.4.1 - Authenticated (Agent+) Privilege Escalation to Administrator via 'connect-customer-to-wp-user' Ability

The LatePoint – Calendar Booking Plugin for Appointments and Events plugin for WordPress is vulnerable to Privilege Escalation in versions up to and including 5.4.1. This is due to a missing authorization check in the execute method of the connect-customer-to-wp-user ability, which only requires...

Dynamic Cyber Ranges

As LLM-driven agents advance in cybersecurity, Jeopardy CTF benchmarks are approaching saturation and cyber ranges, the natural next evaluation frontier, offer diminishing resistance under their current static design. We validate this observation by deploying an LLM-driven Advanced Persistent...

Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat judgement entirely untrained. We present ClawdGo, a framewor...

CVE-2026-6981

A vulnerability was found in IhateCreatingUserNames2 AiraHub2 up to 3e4b77fd7d48ed811ffe5b8d222068c17c76495e. Affected is the function connectstreamendpoint/syncagents of the file AiraHub.py of the component Endpoint. Performing a manipulation results in server-side request forgery. The attack ma...

CVE-2026-6981

A vulnerability was found in IhateCreatingUserNames2 AiraHub2 up to 3e4b77fd7d48ed811ffe5b8d222068c17c76495e. Affected is the function connectstreamendpoint/syncagents of the file AiraHub.py of the component Endpoint. Performing a manipulation results in server-side request forgery. The attack ma...

CVE-2026-6981 IhateCreatingUserNames2 AiraHub2 Endpoint AiraHub.py sync_agents server-side request forgery

A vulnerability was found in IhateCreatingUserNames2 AiraHub2 up to 3e4b77fd7d48ed811ffe5b8d222068c17c76495e. Affected is the function connectstreamendpoint/syncagents of the file AiraHub.py of the component Endpoint. Performing a manipulation results in server-side request forgery. The attack ma...

EUVD-2026-25657

A vulnerability was found in IhateCreatingUserNames2 AiraHub2 up to 3e4b77fd7d48ed811ffe5b8d222068c17c76495e. Affected is the function connectstreamendpoint/syncagents of the file AiraHub.py of the component Endpoint. Performing a manipulation results in server-side request forgery. The attack ma...

AIRA Hub 代码问题漏洞

AIRA Hub is an internet center developed by IhateCreatingUserNames2, designed for discovering and broadcasting MCP tools and A2A skills. There are code vulnerabilities in AIRA Hub, stemming from the function connectstreamendpoint/syncagents in the AiraHub.py file within the component Endpoint...

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model LLM agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorize...

CVE-2026-41264

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific flaw exists within the run method of the CSVAgents class. The issue results from the lack of proper sandboxing when evaluating an LLM generated python script. An attacker can...

CVE-2026-41264

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific flaw exists within the run method of the CSVAgents class. The issue results from the lack of proper sandboxing when evaluating an LLM generated python script. An attacker can...

CVE-2026-41208

Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Versions of @paperclipai/server prior to 2026.416.0 contain a privilege escalation vulnerability that allows an attacker with an Agent API key to execute arbitrary OS commands on the Paperclip serv...

PT-2026-34780

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.3.28 Description An agentic consent bypass allows LLM agents to silently disable execution approval. Remote attackers can exploit this by using the config.patch parameter to bypass security controls and execute...

CVE-2026-41349: Missing Authorization

OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch parameter. Remote attackers can exploit this to bypass security controls and execute unauthorized operations without user consent...

Flowise 安全漏洞

Flowise is an open-source tool developed by FlowiseAI, designed for easily building LLM applications. Prior versions of Flowise, up to 3.1.0, contained a security vulnerability. This vulnerability stemmed from the lack of proper sandboxing mechanisms in the run method of the CSVAgents class,...

Flowise 命令注入漏洞

Flowise is an open-source tool developed by FlowiseAI, designed for easily building LLM applications. Prior to Flowise 3.1.0, there was a command injection vulnerability in versions of the tool. This vulnerability stemmed from the lack of proper sandboxing mechanisms in the run method of the...

Toxic Combinations: When Cross-App Permissions Stack into Risk

On January 31, 2026, researchers disclosed that Moltbook, a social network built for AI agents, had left its database wide open, exposing 35,000 email addresses and 1.5 million agent API tokens across 770,000 active agents. The more worrying part sat inside the private messages. Some of those...

Taint-Style Vulnerability Detection and Confirmation for Node.Js Packages Using LLM Agent Reasoning

The rapidly evolving Node$.$js ecosystem currently includes millions of packages and is a critical part of modern software supply chains, making vulnerability detection of Node$.$js packages increasingly important. However, traditional program analysis struggles in this setting because of dynamic...