1487 matches found
CVE-2026-56340: Improper Input Validation
vLLM versions = 0.10.2 and 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed negative or out-of-bounds tensor indices, when the...
PT-2026-51172
Name of the Vulnerable Software and Affected Versions vLLM versions 0.10.2 through 0.12.x Description Multimodal embeddings processing lacks sparse tensor validation. Since PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests containing...
CVE-2025-71379: Inefficient Regular Expression Complexity
vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker...
PT-2026-90009
Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp. This link is maintained to preserve external references. Original Description vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several...
GHSA-M6QW-4CW2-HM4M vulnerabilities
Vulnerabilities for packages: airflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.9, py3.13-scanner-test-libraries-aiohttp, lmcache-cuda-12.8, py3-vllm-cuda-13.0, airflow-core, py3-vllm-cuda-12.4...
CVE-2026-50269 vulnerabilities
Vulnerabilities for packages: airflow, tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.9, py3.13-scanner-test-libraries-aiohttp, lmcache-cuda-12.8, py3-vllm-cuda-13.0, airflow-core, py3-vllm-cuda-12.4...
Duplicate Advisory: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations
Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-8jr5-v98p-w75m. This link is maintained to preserve external references. Original Description A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from...
Improper Handling of Highly Compressed Data (Data Amplification)
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 Handling of Highly Compressed Data Data Amplification through the audio.py file. An attacker can cause excessive memory consumption by...
GHSA-6PR9-RP53-2PMC vLLM: OOM Denial of Service via Audio Decompression Bomb
Summary vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to 14.9GB of float32 PCM at decode time. Tested on vLLM v0.19.0. Details SpeechToTextProcessor rejects uploads over VLLMMAXAUDIOCLIPFILESIZEMB default 25MB based on...
GHSA-HGG8-FQQC-VFMW vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via the Anthropic API router Researcher: Kai Aizen — SnailSploit @SnailSploit, Adversarial & Offensive Security Research Severity: CVSS 3.1 5.3 Medium AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N Target: https://github.com/vllm-project/vllm ---...
Incorrect Conversion between Numeric Types
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Incorrect Conversion between Numeric Types in the ggmldequantize, ggmlmulmatveca8, ggmlmulmata8, and ggmlmoea8 functions when tensor dimensions are...
Interpretation Conflict
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Interpretation Conflict in the image processing pipeline. An attacker can cause the model to interpret images differently from human expectations by...
Improper Validation of Specified Type of Input
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 Specified Type of Input due to improper validation of the temperature parameter while sampling. An attacker can cause the...
vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
Summary All 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 propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors tha...
CVE-2026-12491 Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency tRNS data, during image processing. When images are converted to RGB, transparency informatio...
CVE-2026-53540 vulnerabilities
Vulnerabilities for packages: wazuh-manager, airflow, tritonserver-backend-vllm-cuda-12.9, airflow-postgres-fips, wazuh-manager-fips, airflow-core, litellm...
GHSA-V9PG-7XVM-68HF vulnerabilities
Vulnerabilities for packages: wazuh-manager, airflow, tritonserver-backend-vllm-cuda-12.9, airflow-postgres-fips, wazuh-manager-fips, airflow-core, litellm...
CVE-2026-53537 vulnerabilities
Vulnerabilities for packages: wazuh-manager, airflow, tritonserver-backend-vllm-cuda-12.9, airflow-postgres-fips, wazuh-manager-fips, airflow-core, litellm...