Your LLM Agent Can Leak Your Data: Data Exfiltration Via Backdoored Tool Use

Tool-use large language model LLM agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats, the risk of systematic data exfiltration by backdoored...

MA-IDS: Multi-Agent RAG Framework for IoT Network Intrusion Detection with an Experience Library

Network Intrusion Detection Systems NIDS face important limitations. Signature-based methods are effective for known attack patterns, but they struggle to detect zero-day attacks and often miss modified variants of previously known attacks, while many machine learning approaches offer limited...

PT-2026-31721

Name of the Vulnerable Software and Affected Versions wolfSSL versions prior to 5.9.1 Description Missing hash/digest size and Object Identifier OID checks allow digests smaller than allowed when verifying ECDSA certificates, or smaller than appropriate for the relevant key type, to be accepted b...

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills

OpenClaw's ClawHub marketplace hosts over 13,000 community-contributed agent skills, and between 13% and 26% of them contain security vulnerabilities according to recent audits. Regex scanners miss obfuscated payloads; formal static analyzers cannot read the natural language instructions in...

PT-2026-31016

Name of the Vulnerable Software and Affected Versions OpenTelemetry-Go versions 1.36.0 through 1.40.0 Description The OpenTelemetry-Go implementation is susceptible to a remote request amplification issue due to the way it handles multi-value baggage headers. Specifically, the extractMultiBaggage...

EUVD-2026-19472

SymCrypt is the core cryptographic function library currently used by Windows. From 103.5.0 to before 103.11.0, The SymCryptXmssSign function passes a 64-bit leaf count value to a helper function that accepts a 32-bit parameter. For XMSS^MT parameter sets with total tree height = 32 which include...

CVE-2026-35199

SymCrypt is the core cryptographic function library currently used by Windows. From 103.5.0 to before 103.11.0, The SymCryptXmssSign function passes a 64-bit leaf count value to a helper function that accepts a 32-bit parameter. For XMSS^MT parameter sets with total tree height = 32 which include...

DPRK-Linked Hackers Use GitHub as C2 in Multi-Stage Attacks Targeting South Korea

Threat actors likely associated with the Democratic People's Republic of Korea DPRK have been observed using GitHub as command-and-control C2 infrastructure in multi-stage attacks targeting organizations in South Korea. The attack chain, per Fortinet FortiGuard Labs, involves obfuscated Windows...

Multi-OS Cyberattacks: How SOCs Close a Critical Risk in 3 Steps

Your attack surface no longer lives on one operating system, and neither do the campaigns targeting it. In enterprise environments, attackers move across Windows endpoints, executive MacBooks, Linux infrastructure, and mobile devices, taking advantage of the fact that many SOC workflows are still...

SigCorr 0.1.0

SigCorr detects cross-protocol attack chains spanning SS7/MAP, Diameter S6a, and GTPv2-C interfaces in mobile core networks. It performs unified subscriber identity correlation across protocol boundaries to detect multi-stage attacks that single-interface monitors miss. It is written in Java 17 a...

PT-2026-41194

Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.9.0 Description An authorization issue allows any authenticated user with low privileges to enumerate active background tasks across the system and stop tasks belonging to other users. This occurs because the...

A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection

Open-source libraries are widely used in modern software development, introducing significant security vulnerabilities. While static analysis tools can identify potential vulnerabilities at scale, they often generate overwhelming reports with high false positive rates. Automated Exploit Generatio...

CVE-2026-5586 zhongyu09 openchatbi Multi-stage Text2SQL Workflow sql injection

A vulnerability was determined in zhongyu09 openchatbi up to 0.2.1. The impacted element is an unknown function of the component Multi-stage Text2SQL Workflow. Executing a manipulation of the argument keywords can lead to sql injection. The attack may be launched remotely. The exploit has been...

CVE-2026-5586 zhongyu09 openchatbi Multi-stage Text2SQL Workflow sql injection

A vulnerability was determined in zhongyu09 openchatbi up to 0.2.1. The impacted element is an unknown function of the component Multi-stage Text2SQL Workflow. Executing a manipulation of the argument keywords can lead to sql injection. The attack may be launched remotely. The exploit has been...

NetSecBed: A Container-Native Testbed for Reproducible Cybersecurity Experimentation

Cybersecurity research increasingly depends on reproducible evidence, such as traffic traces, logs, and labeled datasets, yet most public datasets remain static and offer limited support for controlled re-execution and traceability, especially in heterogeneous multi-protocol environments. This...

Beamforming Feedback As a Novel Attack Surface for Wi-Fi Physical-Layer Security

With the rapid evolution of wireless technologies, Wi-Fi has expanded beyond its original role in data transmission to support various emerging applications, particularly in physical-layer security, including device authentication, user authentication, and secret key generation. Despite extensive...

CVE-2026-5586: Improper Neutralization of Special Elements used in an SQL Command

A vulnerability was determined in zhongyu09 openchatbi up to 0.2.1. The impacted element is an unknown function of the component Multi-stage Text2SQL Workflow. Executing a manipulation of the argument keywords can lead to sql injection. The attack may be launched remotely. The exploit has been...

Your Agent Is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt...

Towards Predicting Multi-Vulnerability Attack Chains in Software Supply Chains from Software Bill of Materials Graphs

Software supply chain security compromises often stem from cascaded interactions of vulnerabilities, for example, between multiple vulnerable components. Yet, Software Bill of Materials SBOM-based pipelines for security analysis typically treat scanner findings as independent per-CVE Common...

CVE-2026-34953

PraisonAI is a multi-agent teams system. Prior to version 4.5.97, OAuthManager.validatetoken returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated as authenticated, granting full access t...