Memory Allocation with Excessive Size Value

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Memory Allocation with Excessive Size Value via image decompression bomb handling in loadbytes in vllm/multimodal/media/image.py and the video frame...

Reachable Assertion

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Reachable Assertion via a P0/P1 multimodal processor cache drift condition in vllm/multimodal/cache.py and the V1 engine core. When the frontend P0...

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...

Denial of Service (DoS)

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Denial of Service DoS via the computeframesindextosample method in vllm/multimodal/video.py, where the GLMGAVideoBackend class applies no upper boun...

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...

CVE-2026-44222

vLLM is an inference and serving engine for large language models LLMs. From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder...

CVE-2026-22778

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 heap address. With this leak, we reduce ASLR from 4 billion guess...

CVE-2025-6242

The CVE-2025-6242 SSRF vulnerability targets vLLM's MediaConnector (load_from_url/load_from_url_async) allowing user-supplied URLs to trigger server-side requests to internal resources. Concrete details: the issue arises from insufficient host restriction on mediaURL fetches, enabling potential a...

CVE-2025-6242 Vllm: server side request forgery (ssrf) in mediaconnector

A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows an...

CVE-2025-46722

vLLM is an inference and serving engine for large language models LLMs. In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image...

CVE-2025-46722: Improper Validation of Consistency within Input

vLLM is an inference and serving engine for large language models LLMs. In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image...