CVE-2026-61439 漏洞深度分析

漏洞概述

CVE 编号： CVE-2026-61439
CVSS 评分： 8.7（HIGH）
CVSS 向量： CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CWE 分类： CWE-1188
漏洞状态： Deferred
发布时间： 2026-07-11T14:16:22.870
最后更新： 2026-07-14T15:17:08.340

漏洞描述

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financial manipulation that trigger HIGH severity detection but are logged without blocking, enabling system prompt extraction and unauthorized tool invocations.

影响分析

此漏洞的具体影响取决于实际利用场景。"

修复建议

1. 及时关注厂商发布的安全更新和补丁
2. 升级受影响组件到最新版本
3. 如无法立即升级，参考厂商提供的临时缓解措施
4. 加强网络访问控制和监控

参考链接

1. https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-fj8f-m44g-c479
2. https://www.vulncheck.com/advisories/praisonai-before-prompt-injection-defense-bypass
3. https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-fj8f-m44g-c479