Skip to main content
VulnerabilityPublished

CVE-2026-18883: ServiceNow Now Assist for CSM · Improper Neutralization of Input Used for LLM Prompting

Affects ServiceNow Now Assist for CSMSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 7.1 High : upgrade to SR - CSM - Customer Service Management AI agent collection v6.1 soon.

Data as of 19 Nov 2026, 20:20 UTC

CVSS 4.0 base score
7.1High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (SN)CVSS 4.07.1
Patch
Available – fixed in SR - CSM - Customer Service Management AI agent collection v6.1
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 19 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 18 Nov 2026.

What to do

Upgrade ServiceNow Now Assist for CSM to SR - CSM - Customer Service Management AI agent collection v6.1.

Affected software

ProductAffectedFixed in
ServiceNowNow Assist for CSMAffected
  • =0
Fixed in
  • SR - CSM - Customer Service Management AI agent collection v6.1

AI-suggested

ServiceNow has already deployed a central remediation for this vulnerability in the Email Response AI Agent of Now Assist for CSM. No platform version upgrade or hotfix is required by customers. Users should verify that their ServiceNow instances are using the updated AI agent collection version 6.1 or later. Since this is a cloud service, ServiceNow manages the remediation process server-side.

Description

CVE-2026-18883 is a high-severity vulnerability in ServiceNow's Now Assist for CSM, specifically in the Email Response AI Agent. It involves improper neutralization of input used for large language model (LLM) prompting, classified as CWE-1427. The issue was addressed by ServiceNow through a centrally deployed remediation that does not require platform upgrades or hotfixes. There are no known exploits in the wild at this time.

References

Community reviews

Loading reviews…