
Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD description
ServiceNow has addressed an indirect prompt injection security issue that was identified in the Email Response AI Agent of Now Assist for CSM. We are not currently aware of malicious exploitation against ServiceNow instances. This remediation was deployed centrally to the Email Response AI Agent (Now Assist for CSM) and does not require a platform version upgrade or hot fix; no version-specific backports apply.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
NONE
Momentum
NONE

11月19日,ServiceNow 发布安全更新修复 AI 平台两处高危漏洞,均出自内部安全测试与漏洞赏金计划。 CVE-2026-125288 是代码注入漏洞,拥有模板编辑权限的已认证用户可在另一用户会话上下文中执行代码,攻击面限于实例内部而非公网。 CVE-2026-18883 是 Now Assist for CSM 邮件应答 AI 智能体的间接提示注入,藏在邮件内容里的指令会被模型当作操作者命令执行。 两处漏洞仅影响 Australia 产品线,AI 平台需升级到 Patch 5 或 5a,云托管实例已自动部署修复;邮件智能体则在插件侧直接修复,无需平台升级。 ServiceNow 表示暂未发现漏洞已被实际利用,自托管客户仍应尽快应用补丁,避免 AI 工作流成为攻击入口。