PYSEC-2026-4310 vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

Summary An unauthenticated remote attacker can exhaust the memory of the vLLM API-server process by raising the request-level mediaiokwargs.video.maxframes and fps knobs on any deployment serving a Qwen2-VL or Qwen3-VL model. 74 extra bytes of JSON took the server's peak RSS from 2 271 MiB to 13...

safety-awareness

Transfer Safety Awareness for Cross-Modal Safety Drift Official implementation of Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models EMNLP 2026 Findings. This repository contains the Qwen3-VL safety-awareness direction pipeline. It extracts a refusal-relate...

GHSA-X6MC-67GF-CHW4 vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

Summary An unauthenticated remote attacker can exhaust the memory of the vLLM API-server process by raising the request-level mediaiokwargs.video.maxframes and fps knobs on any deployment serving a Qwen2-VL or Qwen3-VL model. 74 extra bytes of JSON took the server's peak RSS from 2 271 MiB to 13...

vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

Summary An unauthenticated remote attacker can exhaust the memory of the vLLM API-server process by raising the request-level mediaiokwargs.video.maxframes and fps knobs on any deployment serving a Qwen2-VL or Qwen3-VL model. 74 extra bytes of JSON took the server's peak RSS from 2 271 MiB to 13...

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the computeframesindextosample method in vllm/multimodal/video.py, where the fps and...

CVE-2026-105758 vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the mediaiokwargs.video.maxframes and mediaiokwargs.video.fps fields without enforcing server-side ceilings. An...

CVE-2026-105758 vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach

vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept request-level values for the mediaiokwargs.video.maxframes and mediaiokwargs.video.fps fields without enforcing server-side ceilings. An...

CVE-2026-105758

The vLLM inference engine (versions 0.24.0 through 0.30.0 ) is vulnerable to a resource exhaustion issue within the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes. The software fails to enforce server-side ceilings on media_io_kwargs.video.max_frames and media_io_kwargs.video.fps fields prov...

Sleeping Secrets: How Fine-Tuning Reawakens Privacy Risks in Language Models

Beyond adapting Large Language Models LLMs to specialized applications, fine-tuning has recently been shown to recover private information that is no longer accessible through direct queries. Previous fine-tuning recovery attacks, however, require genuine private supervision drawn from the same...

DistillGuard: Malicious NPM Package Detection and API Attack Chain Analysis Via Static Graph and LLM Distillation

The Node.js ecosystem heavily relies on NPM packages, and software supply chain attacks targeting malicious NPM packages are rampant. Malicious code primarily triggers during package installation, import, and runtime. Traditional static analysis fails to understand code semantics; machine...

vLLM has Remote DoS via Invalid Recovered Token Reinjection

SummaryA frontend-legal multi-request speculative workload can make vLLM produce an out-of-vocabulary recovered token equal to vocabsize, convert that value to -1 when choosing the next live token for a request, and then feed that -1 back into the next drafter input ids. On Qwen3 GPTQ this reache...

vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

SummaryAn unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

PYSEC-2026-2014 vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

Summary An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

Maestro 0.17.1

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...

ado-vllm-performance (>=1.2.2, <=1.3.3), caption-flow (>=0.5.0, <=0.5.1) +23 more potentially affected by CVE-2026-12491 via vllm (>=0.11.0, <=0.23.0)

vllm PYPI version =0.11.0, =1.2.2, =0.5.0, =0.3.9.post2, =0.5.2, =0.1.0, =0.2.4, =2.5.3, =0.0.2, =0.1.0, =0.1.0, =0.2.0 and more Source cves: CVE-2026-12491 Source advisory: OSV:GHSA-8JR5-V98P-W75M...

Maestro 0.15.4

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...

EUVD-2025-29456

Malicious code in bioql PyPI...

GHSA-79J6-G2M3-JGFW vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

Summary An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

CVE-2025-9141

A vulnerability was found in vLLM's Qwen3 Coder tool parser. Since this parser uses Python's eval function, it poses a risk of arbitrary code execution. This vulnerability appears during the parameter conversion process when the parser attempts to handle complex data types...