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 processin
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 UR
An Out-Of-Memory (OOM) vulnerability exists in the `ollama` server version 0.3.14. This vulnerability can be triggered when a malicious API server responds with a gzip bomb HTTP response, leading to t
A vulnerability was identified in vllm-project vllm 0.19.0. This issue affects some unknown processing of the component OpenAI-compatible Serving Path. Such manipulation leads to denial of service. It
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 lac
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 th
OpenClaw versions prior to 2026.2.14 decode base64-backed media inputs into buffers before enforcing decoded-size budget limits, allowing attackers to trigger large memory allocations. Remote attacker
vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request w
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addr
An out-of-bounds read in the read_global_param() function (libavcodec/av1dec.c) of FFmpeg v8.0.1 allows attackers to cause a Denial of Service (DoS) via a crafted input.
A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based
A heap buffer overflow in the av_bprint_finalize() function of FFmpeg v8.0.1 allows attackers to cause a Denial of Service (DoS) via a crafted input.
A heap buffer overflow vulnerability in FFmpeg before commit 4bf784c allows attackers to trigger a memory corruption via supplying a crafted media file in avformat when processing tile grid group stre
A Denial of Service (DoS) vulnerability exists in the file upload feature of haotian-liu/llava, specifically in Release v1.2.0 (LLaVA-1.6). The vulnerability is due to improper handling of form-data w
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 Open
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 vL
Ollama 0.11.5-rc0 through current version 0.13.5 contain a null pointer dereference vulnerability in the multi-modal model image processing functionality. When processing base64-encoded image data via
A vulnerability was found in FFmpeg up to 7.0.1. It has been classified as critical. This affects the function pnm_decode_frame in the library /libavcodec/pnmdec.c. The manipulation leads to heap-base
vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potenti
A heap overflow in the MatroskaFile::createRTPSinkForTrackNumber() function of Live555 Streaming Media v2018.09.02 allows attackers to cause a Denial of Service (DoS) via supplying a crafted MKV file.
Page 1+ Next →