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
PraisonAI AgentLoop onToolCall approval runs after tool execution
Vulnerability Description
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Vulnerability Type
保护机制失效
Vulnerability Title
Mervin Praison PraisonAI 处理逻辑错误漏洞
Vulnerability Description
Mervin Praison PraisonAI是Mervin Praison个人开发者开源的一个低代码多智能体协作框架。 Mervin Praison PraisonAI 1.4.0版本至1.7.2之前版本存在安全漏洞,该漏洞源于src/praisonai-ts/src/ai/agent-loop.ts中的createAgentLoop()在调用onToolCall审批回调之前将可执行工具传递给generateText(),导致已拒绝的工具仍被封装的AI SDK在生成期间执行,可能绕过审批执行被拒绝的文
CVSS Information
N/A
Vulnerability Type
N/A