ACIArena: Toward Unified Evaluation for Agent Cascading Injection

Collaboration and information sharing empower Multi-Agent Systems MAS but also introduce a critical security risk known as Agent Cascading Injection ACI. In such attacks, a compromised agent exploits inter-agent trust to propagate malicious instructions, causing cascading failures across the...

Directory Traversal

Overview praisonai is a PraisonAI TypeScript AI Agents Framework - Node.js, npm, and Javascript AI Agents Framework Affected versions of this package are vulnerable to Directory Traversal in the MultiAgentLedger and MultiAgentMonitor components. An attacker can access sensitive context data...

PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling

Summary The MultiAgentLedger and MultiAgentMonitor components in the provided code exhibit vulnerabilities that can lead to context leakage and arbitrary file operations. Specifically: 1. Memory State Leakage via Agent ID Collision: The MultiAgentLedger uses a dictionary to store ledgers by agent...

GHSA-766V-Q9X3-G744 PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling

Summary The MultiAgentLedger and MultiAgentMonitor components in the provided code exhibit vulnerabilities that can lead to context leakage and arbitrary file operations. Specifically: 1. Memory State Leakage via Agent ID Collision: The MultiAgentLedger uses a dictionary to store ledgers by agent...

Benchmarking-Agent-Architectures

Benchmarking Agent Architectures for LLM-Based Exploit Gener...

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...

PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy

While recent approaches leverage large language models LLMs and multi-agent pipelines to automatically generate proof-of-concept PoC exploits from vulnerability reports, existing systems often suffer from two fundamental limitations: unreliable validation based on surface-level execution signals...

Argus: Reorchestrating Static Analysis Via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection

Recent advancements in Large Language Models LLMs have sparked interest in their application to Static Application Security Testing SAST, primarily due to their superior contextual reasoning capabilities compared to traditional symbolic or rule-based methods. However, existing LLM-based approache...

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...

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...

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...

CVE-2026-34934

PraisonAI is a multi-agent teams system. Prior to version 4.5.90, the getalluserthreads function constructs raw SQL queries using f-strings with unescaped thread IDs fetched from the database. An attacker stores a malicious thread ID via updatethread. When the application loads the thread list, t...

agentic-blocks (>=0.1.36 <=0.1.37), aiqtoolkit-agno (>=1.1.0 <=1.3.1) +9 more potentially affected by CVE-2026-35002 via agno (>=1.2.16 <=2.0.9)

agno PYPI version =1.2.16, =0.1.36, =1.1.0, =0.8.0, =0.1.0, =1.3.4, =0.1.0.post1, =1.1.0a20251020, =1.7.0a20260513 - synvya-sdk =0.2.12 Source cves: CVE-2026-35002 Source advisory: OSV:GHSA-77RH-M34W-RV36...

Agentic-Security-Code-Review

🔍 Agentic Security Code Review !Claude Codehttps://img.sh...

Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-Agent AI Systems

As Large Language Models LLMs and multi-agent AI systems are demonstrating increasing potential in cybersecurity operations, organizations, policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such AI systems to...

Red-MIRROR: Agentic LLM-Based Autonomous Penetration Testing with Reflective Verification and Knowledge-Augmented Interaction

Web applications remain the dominant attack surface in cybersecurity, where vulnerabilities such as SQL injection, XSS, and business logic flaws continue to cause significant data breaches. While penetration testing is effective for identifying these weaknesses, traditional manual approaches are...

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

LLM-based multi-agent systems MASs are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal data and services, but this autonomy introduces significant...

Langflow 安全漏洞

Langflow is an open-source visualization framework developed by Langflow for building multi-agent and RAG applications. Versions of Langflow prior to 1.5.1 contained security vulnerabilities. These vulnerabilities stemmed from a lack of ownership checks in the readflow assistant, which could allo...

Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing

The increasing complexity and interconnectivity of digital infrastructures make scalable and reliable security assessment methods essential. Robotic systems represent a particularly important class of operational technology, as modern robots are highly networked cyber-physical systems deployed in...

SoK: The Attack Surface of Agentic AI -- Tools, and Autonomy

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation RAG, and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we m...