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 FencerCISA 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
- CVE List CVE-2026-18883
- NVD CVE-2026-18883
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.