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...

Seclens: Role-Specific Evaluation of LLM'S for Security Vulnerablity Detection

Existing benchmarks for LLM-based vulnerability detection compress model performance into a single metric, which fails to reflect the distinct priorities of different stakeholders. For example, a CISO may emphasize high recall of critical vulnerabilities, an engineering leader may prioritize...

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...

vLLM 输入验证错误漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Versions of vLLM prior to 0.5.5 and 0.18.0 contained a vulnerability related to input validation errors. This vulnerability stemmed from inconsistencies in the audio mono downmi...

DEBIAN-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...

UBUNTU-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...

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

System Instructions in Large Language Models LLMs are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive information such as API credentials, internal policies, and...

Quantum-Safe Code Auditing: LLM-Assisted Static Analysis and Quantum-Aware Risk Scoring for Post-Quantum Cryptography Migration

The impending arrival of cryptographically relevant quantum computers CRQCs threatens the security foundations of modern software: Shor's algorithm breaks RSA, ECDSA, ECDH, and Diffie-Hellman, while Grover's algorithm reduces the effective security of symmetric and hash-based schemes. Despite NIS...

The vulnerability of the getTableSchemaSql() function in the LLM system, which allows attackers to execute arbitrary SQL commands.

The vulnerability of the getTableSchemaSql function in the large language model LLM running and management system is related to the lack of measures taken to protect the SQL query structure. Exploiting this vulnerability allows a malicious actor to execute arbitrary SQL commands remotely...

The vulnerability in the frontend/src/utils/chat/markdown.js script of the LLM system’s launch and management framework, which allows attackers to perform cross-site scripting (XSS) attacks.

The vulnerability in the frontend/src/utils/chat/markdown.js script of the LLM system’s startup and management mechanism is related to insufficient protection of the web page structure. Exploiting this vulnerability could allow a malicious actor to perform XSS attacks across different websites...

The vulnerability of the ImportedPlugin.importCommunityItemFromUrl() function in the LLM system’s runtime and management framework allows a malicious actor to execute arbitrary code.

The vulnerability of the ImportedPlugin.importCommunityItemFromUrl function in the LLM system is related to an incorrect restriction on the path name of the catalog. Exploiting this vulnerability could allow a malicious actor to execute arbitrary code...

The vulnerability of the LLM system for launching and managing large language models (LLM) allows a perpetrator to gain unauthorized access to protected information.

The vulnerability of LLM-powered systems is related to configuration errors in CORS policies. Exploiting this vulnerability can allow an attacker to gain unauthorized access to protected information...

The vulnerability of LLM-powered system startups, related to deficiencies in authentication mechanisms, allows attackers to view and modify settings.

The vulnerability of LLM-based system startups is related to deficiencies in authentication mechanisms. Exploiting this vulnerability allows a remote attacker to view and modify system settings...