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
DSPy 3.3.0b1 Local File Read via Image/Audio Output Field Parsing
Vulnerability Description
DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The JSONAdapter and ChatAdapter parse untrusted language model completions through parse_value into TypeAdapter validation, which triggers encode_image or encode_audio to read and base64-encode any local file path via the os.path.isfile branch in image.py and audio.py, subsequently embedding the file contents into outgoing prompt messages sent to the attacker-controlled model endpoint.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
Vulnerability Type
文件名或路径的外部可控制
Vulnerability Title
Stanford NLP dspy 输入验证错误漏洞
Vulnerability Description
Stanford NLP dspy是美国Stanford NLP大学开源的一个构建语言模型管道的声明式编程框架。 Stanford NLP dspy 3.3.0b1版本存在输入验证错误漏洞,该漏洞源于Image和Audio输出字段适配器未能正确验证url字段,可能导致攻击者通过注入文件系统路径读取任意本地文件。
CVSS Information
N/A
Vulnerability Type
N/A