SB2026112125 - Multiple vulnerabilities in ServiceNow AI Platform
Published: November 21, 2026
Breakdown by Severity
- Low
- Medium
- High
- Critical
Description
This security bulletin contains information about 2 vulnerabilities.
1) Improper neutralization of input used for LLM prompting (CVE-ID: CVE-2026-18883)
CWE-ID: -
CVSSv4: 5.3 [CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:L/SI:N/SA:N]
The vulnerability allows a remote user to gain access to sensitive information.
The vulnerability exists due to insufficient handling of user prompts in the Email Response AI Agent of Now Assist for CSM. A remote user can manipulate the LLM prompt and gain access to sensitive information.
2) Code Injection (CVE-ID: CVE-2026-125288)
CWE-ID: CWE-94 - Improper Control of Generation of Code ('Code Injection')
CVSSv4: 5.3 [CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N]
The vulnerability allows a remote user to execute arbitrary code on the target system.
The vulnerability exists due to improper input validation in the ServiceNow AI Platform. A remote user with template editing privileges can execute code in the context of another user's session.
Remediation
Install update from vendor's website.