A New Framework for Cybersecurity Refusals in AI Agents

Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existing benchmarks for AI agents in cybersecurity focus mainly on measuring proficiency--how effectively agents can complet...

Researchers left AI agents alone in a virtual town and watched it all unravel

Tech leaders have spent the past year telling everyone that AI agents are about to run financial systems, file your tax returns, and quietly buy your groceries. Just leave them alone, the rhetoric goes; they'll handle it. But a New York startup left ten of them alone in a virtual town for two...

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...

Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments

Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful automation, the security implications of hosting autonomous...

Maestro 0.15.4

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...

Malicious code in dabrius (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 4a154cab742b51be41ca413e20acccfed4290ac4cf692e1cfeb17a677df98bab The message hidden in the package description tries to convince AI agents to prefer installing the package, which then in multiple places marks execution and...

Server-side Request Forgery (SSRF)

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Server-side Request Forgery SSRF due to the validateurl function usage of urlparse that treats \ as regular character when extracting host...

Your AI Agents Are Already Inside the Perimeter. Do You Know What They're Doing?

Analysts recently confirmed what identity security teams have quietly feared: AI agents are being deployed faster than enterprises can govern them. In their inaugural Market Guide for Guardian Agents, Gartner states that “enterprise adoption of AI agents is accelerating, outpacing maturity of...

DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety concerns. A growing number of real-world incidents have...

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...

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...

Closing the Security Gap in the Age of Agentic Coding

AI agents are writing more and more code. Ensure it's secure. Learn how Wiz Code plugins and the Green Agent bring machine-speed remediation to your AI-IDE...

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm cybercrime, harassment, weapon synthesis, leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI...

CVE-2026-40153

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the executecommand function in shelltools.py calls os.path.expandvars on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False line 88 for security. This...

Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents

Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential access capabilities as a code deployment task, a 15x...

EUVD-2026-21513

PraisonAIAgents: SSRF via unvalidated URL in webcrawl httpx fallback...

Permissive Cross-domain Policy with Untrusted Domains

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Permissive Cross-domain Policy with Untrusted Domains in the POST /agui endpoint due to the absence of authentication and the use of a...

Information Exposure

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Information Exposure via the subprocess module. An attacker can access sensitive environment variables, including API keys and credentials, ...

Directory Traversal

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Directory Traversal via the listfiles function when the pattern parameter is not properly validated before being passed to Path.glob. An...

Exposure of Sensitive Information Through Environmental Variables

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Exposure of Sensitive Information Through Environmental Variables in the executecommand function, where environment variables within command...