Skip to content
Fencer Intel
high 7.1

CVE-2026-18883 json

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

published 5h ago modified 4h ago also EUVD-2026-130572

cvss
7.1
version 4.0, CNA
cisa kev
Not listed
not in CISA's catalog
epss
—
no EPSS score yet
public exploits
0
none known

Summary

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.

Patch / fix

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

Is CVE-2026-18883 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
4h ago

CVSS scores

assigned by version score vector
CNA 4.0 7.1 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

Affected products

  • ServiceNow Now Assist for CSM

Classification

Weakness
  • CWE-1427 Improper Neutralization of Input Used for LLM Prompting

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.