MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation,...

Trust Me, Import This: Dependency Steering Attacks Via Malicious Agent Skills

LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which attackers may register as malicious packages. In this...

The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents

This position paper argues that the Authorization-Execution Gap AEG is a major safety and security problem in open-world agents. The AEG is the divergence between what a principal intends to authorize and what an open-world agent ultimately executes. Because such agents act autonomously across...

Skill Description Deception Attack against Task Routing in Internet of Agents

A new paradigm, Internet of Agents IoA, is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced...

AgentShield: Deception-Based Compromise Detection for Tool-Using LLM Agents

Defenses against indirect prompt injection IPI in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such ...

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...

CVE-2026-44338 PraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow execution

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...

EUVD-2026-28641

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...

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...

CVE-2026-44338 PraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow execution

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...

EUVD-2026-28454

Improper access control in Azure AI Foundry M365 published agents allows an unauthorized attacker to elevate privileges over a network...

MiracleLinux 9 : fence-agents-4.10.0-98.el9_7.13 (AXSA:2026-575:08)

The remote MiracleLinux 9 host has packages installed that are affected by a vulnerability as referenced in the AXSA:2026-575:08 advisory. pyasn1: pyasn1 Vulnerable to Denial of Service via Unbounded Recursion CVE-2026-30922 Tenable has extracted the preceding description block directly from the...

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...

PraisonAI 访问控制错误漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI from 2.5.6 to 4.6.34 contained an access control vulnerability. This vulnerability stemmed from the Flask API server, which disabled authentication by default, allowing callers without a...

CVE-2026-35435

Improper access control in Azure AI Foundry M365 published agents allows an unauthorized attacker to elevate privileges over a network...

CVE-2026-35435

Improper access control in Azure AI Foundry M365 published agents allows an unauthorized attacker to elevate privileges over a network...

MAL-2026-3369 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...

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...

Azure AI Foundry Elevation of Privilege Vulnerability

Improper access control in Azure AI Foundry M365 published agents allows an unauthorized attacker to elevate privileges over a network...

RLSA-2026:13916 Important: fence-agents security update

The fence-agents packages provide a collection of scripts for handling remote power management for cluster devices. They allow failed or unreachable nodes to be forcibly restarted and removed from the cluster. Security Fixes: pyjwt: PyJWT accepts unknown crit header extensions RFC 7515 ?4.1.11 MU...