CVE-2026-40088

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell...

Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain

Large language model LLM agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers. These routers operate as application-layer proxies with full plaintext access to every in-flight JSON payload, yet no provider enforces cryptographic...

Follow My Eyes: Backdoor Attacks on VLM-Based Scanpath Prediction

Scanpath prediction models forecast the sequence and timing of human fixations during visual search, driving foveated rendering and attention-based interaction in mobile systems where their integrity is a first-class security concern. We present the first study of backdoor attacks against VLM-bas...

LLMtary

LLMtary Elementary — AI-Powered Penetration Testing Platform...

VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database

Software vulnerabilities continue to pose significant threats to modern information systems, requiring a timely and accurate risk assessment. Public repositories, such as the National Vulnerability Database and CVE details, are regularly updated, but predominantly utilize relational data models...

SentinelSphere: Integrating AI-Powered Real-Time Threat Detection with Cybersecurity Awareness Training

The field of cybersecurity is confronted with two interrelated challenges: a worldwide deficit of qualified practitioners and ongoing human-factor weaknesses that account for the bulk of security incidents. To tackle these issues, we present SentinelSphere, a platform driven by artificial...

CVE-2026-5627 Path Traversal in mintplex-labs/anything-llm

A path traversal vulnerability exists in mintplex-labs/anything-llm versions up to and including 1.9.1, within the AgentFlows component. The vulnerability arises from improper handling of user input in the loadFlow and deleteFlow methods in server/utils/agentFlows/index.js. Specifically, the...

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...

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...

PYSEC-2026-144

vLLM is an inference and serving engine for large language models LLMs. From 0.7.0 to before 0.19.0, the VideoMediaIO.loadbase64 method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The numframes...

CVE-2026-34755

vLLM's VideoMediaIO.load_base64("video/jpeg") path has an unbounded frame-splitting bug: data.split(",") bypasses the intended frame-count limit (default 32) used by the binary path, allowing a single request with thousands of comma-separated base64 JPEG frames. This can cause the server to decod...

SmartContract-VulnHunter

🛡️ SmartContract VulnHunter The ultimate smart contract securi...

vLLM 安全漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.1.0 to 0.19.0 contained security vulnerabilities. These vulnerabilities stemmed from the lack of upper limit validation for the n parameter in the...

whitehathackerai

🛡️ WhiteHatHacker AI Autonomous Bug Bounty Hunter — Power...

Automating Cloud Security and Forensics through a Secure-By-Design Generative AI Framework

As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to meet emerging threats. Large Language Models LLMs have shown promise in automating log analysis and reasoning tasks, yet they remain vulnerable to prompt injection attacks and lack forensic...

SUSE CVE-2026-34159

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserializetensor skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPHCOMPUTE messages. Combined...

PYSEC-2026-2299

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing tomono, while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results...

RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale

Security teams face a challenge: the volume of newly disclosed Common Vulnerabilities and Exposures CVEs far exceeds the capacity to manually develop detection mechanisms. In 2025, the National Vulnerability Database published over 48,000 new vulnerabilities, motivating the need for automation. W...

AgentWatcher: A Rule-Based Prompt Injection Monitor

Large language models LLMs and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: 1 their effectiveness degrades significantly as context length increases, and 2 they lack...