vLLM <= 0.23.0 - Anthropic Router Heap Address Information Leak

vLLM = 0.23.0 incompletely fixes CVE-2026-22778. The original fix added sanitizemessage to the OpenAI router but the Anthropic-compatible router /v1/messages echoes strexc directly. id: CVE-2026-54236 info: name: vLLM = 0.23.0 - Anthropic Router Heap Address Information Leak author: kenlacroix...

EXPLOIT-CVE-2026-22778

CVE-2026-22778 — vLLMの動画処理におけるRCE CVE-2026-22778 （CVSS 9.8）の脆弱性ラボ＋概念実証です。vLLMのマルチモーダル取り込み経路における、認証不要のリモートコード実行チェーンです。 | ---|--- CVE| CVE-2026-22778 アドバイザリ| GHSA-4r2x-xpjr-7cvv 影響を受けるバージョン| vLLM = 0.8.3、 vLLMはメディア読み込みの失敗をHTTP 400に変換し、exc.detailをクライアントにそのまま返していました （apiserver.py）： async def...

CVE-2026-22807_Range

🛡️ CVE-2026-22807 シミュレーション: AI サプライチェーン RCE ターゲットレンジ ⚠️ 免責事項 / Disclaimer 本プロジェクトはセキュリティ研究および教育目的 のみに使用され、AI モデル読み込みプロセスにおけるサプライチェーン攻撃の原理（Remote Code Execution）をデモンストレーションすることを目的としています。 本番環境で生成された悪意のあるモデルを使用しないでください。また、本プロジェクトを違法な攻撃行為に使用することは固く禁じられています。開発者は、不適切な使用によって生じたいかなる法的責任も負いません。 📖 プロジェクト概要...

vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

SummaryThe audio decode-duration guard maxdurations, env VLLMMAXAUDIODECODEDURATIONS, default 600s that protects against audio decompression-bomb DoS is wired into only the speech-to-text path /v1/audio/transcriptions. The chat audio path /v1/chat/completions, inputaudio content parts calls the...

vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation

SummaryCurrent vLLM main lets an inference request choose the PyNvVideoCodec GPU video decoder through mediaiokwargs.video.videobackend, but engine GPU memory reservation is computed only from static startup configuration and VLLMVIDEOLOADERBACKEND. If the server starts with the default...

LeakGauge

LeakGauge 이 저장소는 다음 논문의 코드 저장소입니다: The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges. ArXiv 버전 및 논문 링크: https://arxiv.org/abs/2608.17829 이 저장소는 LeakGauge 누출 탐지 파이프라인을 구현합니다: 데모 데이터셋 준비, 로그 확률log-probability 추출, 프로브 학습, 온라인 또는 오프라인 탐지. 기타 보안 및 안전 작업에 대해서는 SafeGauge를...

CVE-2026-103241

A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely. The exploit has bee...

EUVD-2026-90191

A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely. The exploit has bee...

CVE-2026-103241 vllm-project vLLM Gemma4UnifiedParser gemma4.rs denial of service

A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely. The exploit has bee...

CVE-2026-103241

A flaw in vllm-project vLLM (versions up to 0.26.0 ) affects the Gemma4UnifiedParser component, specifically within the file rust/src/parser/src/unified/gemma4.rs. A remote attacker can execute a manipulation resulting in a denial of service (DoS). Public exploits for this vulnerability have been...

CVE-2026-103241 vllm-project vLLM Gemma4UnifiedParser gemma4.rs denial of service

A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely. The exploit has bee...

CVE-2026-103241 vllm-project vLLM Gemma4UnifiedParser gemma4.rs denial of service

A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely. The exploit has bee...

CVE-2026-103241: Improper Resource Shutdown or Release

A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a manipulation can lead to denial of service. The attack may be launched remotely. The exploit has bee...

ai-kubernetes-helm-chart-security

Kubernetes上のAI: Helmチャートのセキュリティデフォルト（エビデンス） このリポジトリには、Soramiの技術レポート「Kubernetes上のAI: 14個のHelmチャートのうち10個がAPI認証なしで提供されている」（バージョン1.2）の背景となるデータとエビデンスが含まれています。 レポートはこちら: https://sorami.com.au/research/ai-kubernetes-helm-chart-security/...

CVE-2024-11040

CVE-2024-11040 vllm-project vllm 버전 0.5.2.2는 서비스 거부Denial of Service 공격에 취약합니다...

python313-vllm-0.30.0-1.1 on GA media (moderate)

python313-vllm-0.30.0-1.1 on GA media Announcement ID: openSUSE-SU-2026:11867-1 Rating: moderate Cross-References: CVE-2026-90713 CVE-2026-92365 CVE-2026-93841 CVE-2026-93989 CVSS scores: CVE-2026-90713 SUSE : 2.5 CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:N/I:N/A:L CVE-2026-90713 SUSE : 1.9...

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 cachesalt field across multiple API protocol handlers Anthropic, OpenAI chat completion...

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 loadfile in vllm/multimodal/media/audio.py, where the VLLMMAXAUDIOCLIPFILESIZEMB file size...

Use of Less Trusted Source

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Use of Less Trusted Source via incomplete propagation of revision and coderevision pins across artifact boundaries in the model loader subsystem. Wh...

Improper Validation of Array Index

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Improper Validation of Array Index via unvalidated stoptokenids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoint...