vllm vulnerabilities

▾ Sunlitvllm · vllmEPSS 0.48%via NVD

vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities

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 —…

CVE-2026-54235Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.45%via OSV

vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels

CVE-2026-12491Medium· 4.8

▾ Sunlitvllm · vllmEPSS 0.24%via OSV

vLLM: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations

CVE-2026-53923High· 7.5

▾ Twilightvllm · vllmEPSS 0.48%via OSV

vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving

CVE-2026-54236Medium· 5.3PoC

▾ Twilightvllm · vllmEPSS 0.93%via OSV

vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router

CVE-2026-54233Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.42%via OSV

vLLM: OOM Denial of Service via Audio Decompression Bomb

GHSA-x8xr-mj9x-6h7wMedium· 4.8

▾ Sunlitvllm · vllmvia GHSA

Duplicate Advisory: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations

CVE-2026-5497High· 7.5

▾ Twilightvllm · vllmEPSS 0.54%via NVD

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method …

CVE-2026-9540Medium· 5.3

5mo ago

vllm has Improper Resource Shutdown or Release

▾ Sunlitvllm · vllmEPSS 0.43%via OSV

CVE-2026-7141Medium· 5.6

6mo ago

vLLM makes Use of Uninitialized Resource

▾ Sunlitvllm · vllmEPSS 0.29%via OSV

CVE-2026-34756Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.44%via NVD

vLLM is an inference and serving engine for large language models (LLMs)

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the…

CVE-2026-34755Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.48%via NVD

vLLM is an inference and serving engine for large language models (LLMs)

vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPE…

CVE-2026-34753Medium· 5.4PoC

▾ Twilightvllm · vllmEPSS 0.26%via OSV

vLLM: Server-Side Request Forgery (SSRF) in `download_bytes_from_url `

CVE-2026-34760High· 7.1

▾ Twilightvllm · vllmEPSS 0.28%via OSV

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults t…

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 sp…

CVE-2026-27893High· 8.8

▾ Twilightvllm · vllmEPSS 1.4%via NVD

vLLM is an inference and serving engine for large language models (LLMs)

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the…

CVE-2026-25960Medium· 5.4

8mo ago

vLLM has SSRF Protection Bypass

▾ Sunlitvllm · vllmEPSS 0.60%via OSV

CVE-2026-22778Critical· 9.8PoC

▾ Abyssalvllm · vllmEPSS 18%via NVD

vLLM is an inference and serving engine for large language models (LLMs)

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a hea…

CVE-2026-24779High· 7.1

▾ Twilightvllm · vllmEPSS 0.58%via NVD

vLLM is an inference and serving engine for large language models (LLMs)

vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.14.1, a Server-Side Request Forgery (SSRF) vulnerability exists in the `MediaConnector` class within the vLLM project's multimodal feature set. …

CVE-2026-22807High· 8.8PoC

▾ Midnightvllm · vllmEPSS 0.98%via NVD

vLLM is an inference and serving engine for large language models (LLMs)

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_…

CVE-2026-22773Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.44%via NVD

vLLM is an inference and serving engine for large language models (LLMs)

vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a s…

CVE-2025-62372Medium· 6.5

11mo ago

vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

▾ Sunlitvllm · vllmEPSS 0.41%via OSV

CVE-2025-62164High· 8.8

11mo ago

vLLM deserialization vulnerability leading to DoS and potential RCE

▾ Twilightvllm · vllmEPSS 0.96%via OSV

CVE-2025-61620Medium· 6.5

▾ Sunlitvllm · vllmvia OSV

vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server

CVE-2025-6242High· 7.1

▾ Twilightvllm · vllmEPSS 0.25%via OSV

vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class

CVE-2025-9141High· 8.8

▾ Twilightvllm · vllmvia OSV

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

CVE-2025-48887Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.54%via OSV

vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

CVE-2025-46722Medium· 4.2