A flaw was found in the vLLM library. A completions API request with an empty prompt will crash the vLLM API server, resulting in a denial of service.
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 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). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid json_schema as a Guided Param kil
vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to vali
mintplex-labs/anything-llm version git 6dc3642 contains an unauthenticated Denial of Service (DoS) vulnerability in the API for the embeddable chat functionality. An attacker can exploit this vulnerab
A flaw was found in Rustls 0.23.13 and related APIs. This vulnerability allows denial of service (panic) via a fragmented TLS ClientHello message.
A flaw was found in the X server's request handling. Non-zero 'bytes to ignore' in a client's request can cause the server to skip processing another client's request, potentially leading to a denial
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
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
In multiple locations, there is a possible persistent denial of service due to improper input validation. This could lead to local denial of service with no additional execution privileges needed. Use
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
A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. The stream_complete method executes the llm using a thr
An issue was discovered in Malwarebytes 4.6.14.326 and before and 5.1.5.116 and before (and Nebula 2020-10-21 and later). An Out of bounds read in several disassembling utilities causes stability issu
A flaw was found in the 389-ds-base LDAP Server. This issue occurs when issuing a Modify DN LDAP operation through the ldap protocol, when the function return value is not tested and a NULL pointer is
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote c
vLLM is an inference and serving engine for large language models (LLMs). The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in the load_from_url_async method due to inconsistent
A flaw was found in the mod_auth_openidc module for Apache httpd. This flaw allows a remote, unauthenticated attacker to trigger a denial of service by sending an empty POST request when the OIDCPrese
A flaw was found in the soup_multipart_new_from_message() function of the libsoup HTTP library, which is commonly used by GNOME and other applications to handle web communications. The issue occurs wh
Page 1+ Next →