CVE-2026-54235

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.23.1rc0, ll temperature validation gates use comparison operators , which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagat...

CVE-2026-47155

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image...

CVE-2026-54233

Affected software: vLLM (inference/serving engine). Vulnerability: decoding an audio file on the /v1/audio/transcriptions endpoint can cause extreme memory growth. A 25 MB OPUS upload decodes to about 14.9 GB of float32 PCM, because the audio decoder concatenates all frames in memory before retur...

Mind Your Key: An Empirical Study of LLM API Credential Leakage in IOS Apps

The rapid integration of large language models LLMs into mobile applications has introduced a new class of credential security risk: leaked credentials that grant unauthorized access to LLM inference services, causing financial damage to developers. Prior work on credential leakage has focused...

EUVD-2026-35116

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, evaluation create and update mass-assignment allows cross-workspace evaluation takeover. This issue has been patched in version 3.1.2...

EUVD-2026-35113

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, CustomTemplate create and update mass-assignment allows cross-workspace template takeover. This issue has been patched in version 3.1.2...

RECON: An LLM-Enhanced Backward Constraint Analysis Framework

While traditional techniques, such as symbolic execution, provide a principled foundation for precise constraint reasoning in program analysis, they struggle to scale to modern software systems mainly due to path explosion, the need for function modeling, and the loss of semantic intent at...

Steganography without Modification: Hidden Communication Via LLM Seeds

We demonstrate that widely deployed Large Language Model LLM inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions. The channel exploits a structural property of deterministic decoding: pseudo-random number generato...

POISE: Position-Aware Undetectable Skill Injection on LLM Agents

Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A practically dangerous injection must stay invisible: if executing the payload derails the user's legitimate task, the resulting failure signal invite...

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory introduces the risk of memory poisoning, where a single adversarial memory write can exert long-term influence over agent behavior. We present a...

-cascade-scan

cascade-scan AI Agent security evaluation framework — autom...

NeuroLog: Reasoning You Can Audit -- Neuro-Symbolic Vulnerability Discovery Via LLM Facts, Datalog, and SMT

Vulnerability discovery on C/C++ source asks the analyst to choose between heavyweight static analysers, which need a working build before a single query runs, and free-form LLMs, which read source readily but invent details and lose track of cross-function dataflow on real codebases. We present...

Attackers Use LLM Agent for Post-Exploitation After Marimo CVE-2026-39987 Exploit

An unknown threat actor has been observed using a large language model LLM agent to conduct post-compromise actions after obtaining initial access following the exploitation of a publicly-accessible Marimo network using a recently disclosed vulnerability. "The attacker compromised an...

How to Compare the Security of Code Written by Humans to LLM-Generated Code

Large language models LLMs are rapidly transforming how software is created and maintained. Comparing LLM-generated code against human-written standards is essential to determine whether these new tools uphold or erode the security baselines established by professional developers. Yet, we lack a...

Honeyval: A Comprehensive Evaluation Framework for LLM-Powered HTTP Honeypots

Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They enable defenders to construct high-interaction honeypots with low system security risks. However, LLM-powered honeyp...

vLLM 安全漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Version vLLM 0.14.1 contains a security vulnerability caused by the hardcoding of the trustremotecode=True parameter, which may lead to remote code execution...

Automatically Attacking Software Reverse Engineering AI Agents

Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models LLM, agentic systems enabled with tools, such as...

Towards Demystifying and Repairing LLM-In-The-Loop Vulnerabilities

Large Language ModelsLLMs have been actively integrated into modern software systems as critical components. LLM-in-the-loop vulnerabilities, where vulnerabilities are introduced by LLMs and their dependent downstream components, such as frameworks, introduce new risks. Although some benchmark...

MemMorph: Tool Hijacking in LLM Agents Via Memory Poisoning

LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks primarily manipulate the tool metadata, which is easily...

EUVD-2026-31057

NVIDIA TRT-LLM for any platform contains a vulnerability in RPC testing, where an attacker could cause an unsafe deserialization. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure...