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...

GHSA-CC4M-MP48-X7QG Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

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...

CVE-2025-33255

Summary: CVE-2025-33255 affects NVIDIA TensorRT-LLM (any platform) via an MPI server deserialization vulnerability. The impact described across sources includes code execution, denial of service, data tampering, and information disclosure. The NVIDIA security bulletin specifies remediation by upd...

Speed Kills: Exploring Confused Deputy Attacks through Edge AI Accelerators

AI Accelerator AIA are specialized hardware e.g., Tensor Processing Unit TPU, that enable optimal and efficient execution of AI applications and on-device inference. The growing demand for AI applications has led to the widespread adoption of AIAs on Edge or embedded devices on Edge or embedded...

Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries

Detecting memory corruption vulnerabilities in stripped binaries requires recovering object semantics, interprocedural propagation, and feasible triggers from low-level, lossy representations. Recent LLM-based approaches improve code understanding, but reliable detection still requires grounding ...

CVE-2026-44223 vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

vLLM is an inference and serving engine for large language models LLMs. From 0.18.0 to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The...

CVE-2026-43992

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool sendtokens, executecontract, instantiatecontract, uploadwasm, ibctransfer, etc. accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in th...

Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance

Prompt specifications for multi-agent large language model LLM systems carry data contracts and integration logic across many interdependent files but are rarely subjected to structured-inspection rigor. This paper reports a single-system empirical case study of iterative, agent-driven auditing...

LLM 安全漏洞

LLM is a multi-model large language model command-line interaction tool developed by Simon Willison. Versions of LLM 0.27.1 and earlier contain security vulnerabilities. These vulnerabilities stem from the use of the --functions command-line parameter to directly execute unsafe code using the exe...

GHSA-P58C-Q354-6C4F pgAdmin 4 contains local file inclusion (LFI) and server-side request forgery (SSRF) vulnerabilities

Local file inclusion LFI and server-side request forgery SSRF vulnerabilities in pgAdmin 4 LLM API configuration endpoints. User-supplied apikeyfile and apiurl preferences were passed to the LLM provider clients without validation. An authenticated user could read arbitrary server-side files by...

Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing

LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache, batching, prefix sharing, speculative decoding, adapters,...

Skill Description Deception Attack against Task Routing in Internet of Agents

A new paradigm, Internet of Agents IoA, is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced...

CVE-2026-41487 Langfuse: Improper role-based-access control in Langfuse LLM connection management allowed users of role “member” to retrieve stored LLM provider API keys

Langfuse is an open source large language model engineering platform. From version 3.68.0 to before version 3.167.0, there is a role-based-access control flaw in the LLM connection update flow. An authenticated, low-privileged user of role “member” in a project could request the update of an...

EUVD-2026-28647

Langfuse is an open source large language model engineering platform. From version 3.68.0 to before version 3.167.0, there is a role-based-access control flaw in the LLM connection update flow. An authenticated, low-privileged user of role “member” in a project could request the update of an...

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code Via Prompt Optimization

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure production code with relevant weaknesses to avoid in context, we...