A Knowledge-Based Multi-Agent Framework for Security Control Recommendation

Hardening IT on-premises environments can be a daunting task for teams without access to adequate cybersecurity expertise. In this regard, Decision Support Systems DSS with embedded expert knowledge can assist users by guiding them with security recommendations to meet their objectives. This work...

T3MP3ST Multi-Agent Offensive Security Framework

T3MP3ST is a multi-agent offensive-security framework, built to turn the AI coding agent you already run into a zero-day hunter...

Secret Scanner Agent: Extracting Secrets and Access Context from Unstructured Documents

Exposed documents such as emails, chat threads, tickets, and incident notes routinely leak credentials, but during incident response a leaked secret is only half the story. Responders also need to identify the "door'' the secret opens: the account, tenant, endpoint, database, cloud resource, or...

Protecting Microsoft at AI speed: How SFI proactively hardens our cloud

AI models have reached a threshold where they exhibit expert-level capabilities in vulnerability discovery, exploit chaining, and proof-of-concept generation. As AI-powered vulnerability discovery matures, every organization that builds or runs software at scale needs continuous proactive...

Protecting Microsoft at AI speed: How SFI proactively hardens our cloud

AI models have reached a threshold where they exhibit expert-level capabilities in vulnerability discovery, exploit chaining, and proof-of-concept generation. As AI-powered vulnerability discovery matures, every organization that builds or runs software at scale needs continuous proactive...

When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems

While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems MAS face critical security challenges due to vulnerabilities at the agent and interaction levels. Most existing MAS security defenses are built upon two core assumptions: semantically-explicit malicious attacks...

PenKit51

The open-source AI penetration testing platform with 63 deep exp...

Detecting Vulnerability-Inducing Commits Via Multi-Stage Reasoning with LLM-Based Agents

Detecting vulnerability-inducing commits VICs at submission time is critical for improving the security and reliability of software systems. However, this task is highly challenging because it requires reasoning about the semantic impact of code changes from heterogeneous information sources,...

Agentic-SecPBFT: Agentic AI-Driven Proactive Security Framework for Wireless PBFT Consensus in Mobile Ad-Hoc Networks

The standard Practical Byzantine Fault Tolerance PBFT protocol, designed for stable, wired environments, exhibits critical vulnerabilities when deployed in settings like mobile ad-hoc networks, thus making it susceptible to sophisticated threats such as Sybil attacks, Byzantine collusion, and...

ensembleAI-lablab.ai-hackathon

Ensemble AI Autonomous DevSecOps triage, adversarial patching...

VeriChat: An Agentic Conversational AI Assistant for Hardware Security Verification

Hardware security verification is a multi-stage process in which engineers must navigate complex design analyses, threat considerations, and verification strategies. They often need security-focused guidance, yet current verification environments provide little structured support for such...

Hephaestus: Toward a Cybersecurity AI Scientist

Cyber offense is moving to machine speed; cyber research itself is not. Existing AI scientist systems make end-to-end research automation increasingly plausible, but they target relatively stable scientific domains. We argue that AI-native cybersecurity is a different kind of scientific object. I...

MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

Multi-agent systems MAS are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that remain poorly understood and are difficult to defend against. In this paper, we address how defenders should prioritize...

Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems

Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels. The natural defence to these collusion attempts is to monitor plain-text communication, but the efficacy of monitors has been called into doubt by increasingly...

AutoJack Attack Lets One Web Page Hijack AI Agent for Host Code Execution

Microsoft researchers have detailed an exploit chain, named AutoJack, that turns an AI browsing agent into a delivery vehicle for remote code execution. Steer the agent to load an attacker's web page, and that page's JavaScript can reach a privileged local service on the same machine and spawn a...

EUVD-2026-37962

PraisonAI before 1.5.115 contains a path traversal vulnerability in MultiAgentMonitor that fails to sanitize agent IDs when building file paths. Attackers can include traversal sequences like ../ in agent IDs to read, write, or overwrite arbitrary files, enabling sensitive disclosure, denial of...

CVE-2026-56078

CVE-2026-56078 affects PraisonAI prior to 1.5.115, specifically a path traversal vulnerability in the MultiAgentMonitor component. The issue arises because agent IDs are not properly sanitized when building file paths, allowing an attacker to inject traversal sequences (e.g., ../) to access arbit...

Improper Authentication

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System IRS framework that converts alerts from IDS, EDR, and XDR platforms into...

Security Engineering of OpenClaw: Analyzing Attack Surface Expansion and Trust-Boundary Violations

Agentic large language model LLM systems can now execute actions, not only produce text. When model outputs trigger privileged operations such as shell commands, browser automation, or external tool calls, the security problem shifts from alignment alone to system configuration and structural...