361,800
Total CVEs
26,223
Critical
85,816
High
1,626
CISA KEV
1,906
This Week
23 results · Page 1/1
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 n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.
vllm
Atcom 100M IP Phones firmware version 2.7.x.x contains an authenticated command injection vulnerability in the web configuration CGI script that allows attackers to execute arbitrary system commands. Attackers can inject shell commands through the 'cmd' parameter in web_cgi_main.cgi, enabling remote code execution with administrative credentials.
Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting') vulnerability in platcom WP-Asambleas wp-asambleas allows Reflected XSS.This issue affects WP-Asambleas: from n/a through <= 2.85.0.