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...

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-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...

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...

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...

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...

AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning Via Dialectics and Meta-Auditing

Large Language Models LLMs are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a root cause shared by both major mitigation paradigms agent-based debate and retrieval augmentation: reasoning in an ungrounded deliberative space that...

EUVD-2026-13766

mcp-memory-service is an open-source memory backend for multi-agent systems. Prior to version 10.25.1, when the HTTP server is enabled MCPHTTPENABLED=true, the application configures FastAPI's CORSMiddleware with alloworigins='', allowcredentials=True, allowmethods="", and allowheaders="". The...

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 1.9.0 contained a security vulnerability. This vulnerability stemmed from the deleteapikeyroute endpoint, which did not verify the ownership of the...

Memory Poisoning and Secure Multi-Agent Systems

Memory poisoning attacks for Agentic AI and multi-agent systems MAS have recently caught attention. It is partially due to the fact that Large Language Models LLMs facilitate the construction and deployment of agents. Different memory systems are being used nowadays in this context, including...

Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles toward suboptimal routes and increase congestion. To addres...

ProvAgent: Threat Detection Based on Identity-Behavior Binding and Multi-Agent Collaborative Attack Investigation

Advanced Persistent Threats APTs pose critical challenges to modern cybersecurity due to their multi-stage and stealthy nature. While provenance-based detection approaches show promise in capturing causal attack semantics, current threat provenance practices face two paradoxical issues: 1 expert...

AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations

Multi-agent systems MAS powered by LLMs promise adaptive, reasoning-driven enterprise workflows, yet granting agents autonomous control over tools, memory, and communication introduces attack surfaces absent from deterministic pipelines. While current research largely addresses prompt-level...

Coverage-Guided Multi-Agent Harness Generation for Java Library Fuzzing

Coverage-guided fuzzing has proven effective for software testing, but targeting library code requires specialized fuzz harnesses that translate fuzzer-generated inputs into valid API invocations. Manual harness creation is time-consuming and requires deep understanding of API semantics,...