漏洞信息
尽管我们使用了先进的大模型技术,但其输出仍可能包含不准确或过时的信息。神龙努力确保数据的准确性,但请您根据实际情况进行核实和判断。
Vulnerability Title
vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
Vulnerability Description
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_media_domains and allowed_local_media_path protections and allowing server-side requests and reads of arbitrary files accessible to the vLLM process. This issue is fixed in version 0.26.0.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
Vulnerability Type
服务端请求伪造(SSRF)
Vulnerability Title
vLLM 服务端请求伪造漏洞
Vulnerability Description
vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.26.0之前版本存在服务端请求伪造漏洞,该漏洞源于MiMoV2OmniMultiModalProcessor处理器将攻击者控制的图像和音频字符串通过_fetch_image、requests.get和Image.open传递,而不是通过MediaConnector,绕过了allowed_media_domains和allowed_local_media_path保护,可能导致服务器端请求和读取vLLM进程可
CVSS Information
N/A
Vulnerability Type
N/A