CVE-2026-18883

published 19 Nov 2026 · updated 19 Nov 2026

Indirect Prompt Injection in Email Response AI Agent (Now Assist for CSM)

7.1HighCVSS 7.1EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in Now Assist for CSM SR - CSM - Customer Service Management AI agent collection v6.1.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
ServiceNowNow Assist for CSM<SR - CSM - Customer Service Management AI agent collection v6.1SR - CSM - Customer Service Management AI agent collection v6.1

Timeline

Every event on this vulnerability

Related

Other vulnerabilities in ServiceNow, strongest first

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-18883 severity on Zeptric[![CVE-2026-18883](https://zeptric.io/badge/cve/CVE-2026-18883.svg)](https://zeptric.io/cve/CVE-2026-18883)