synced JUST NOW
01 Record

CVE-2026-18883

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

HighPUBLISHEDCNA: SN
CNA base score7.1 CVSS v4.0CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N

02 Description

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

03 Exploitation and scoring

Exploitation
Not assessed. CISA has not published an exploitation assessment for this record, and it is not in the KEV catalog. That is an absence of assessment, not a finding of no risk.
Exploit code listed
—
SSVC decision
Not assessed by CISA
EPSS probability
Not scored by EPSS
EPSS percentile
Not scored by EPSS
NVD base score
The NVD has published no score for this record
NVD CVSS vector
No NVD score to derive
NVD analysis status
Not recorded
Red Hat severity
No Red Hat rating. Red Hat rates the CVEs that affect its products.

Exploit-prediction scores from FIRST. Independent scoring and analysis status from the NVD. Vendor severity from Red Hat. Exploitation assessment and catalog membership from CISA.

04 Metadata

Published
2026-11-19 20:00Z48 MIN AGO
Last updated
2026-11-19 20:00Z48 MIN AGO
Reserved
2026-08-04
Assigning CNA
SN
Record state
PUBLISHED
Severity
High (CVSS 7.1)
CNA CVSS vector
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
Weaknesses
  • CWE-1427Improper Neutralization of Input Used for LLM PromptingBase
Data version
5.2
Document digest
9871a61ec05f585b7a09e4bb747316ef2f915a15dd50db04a1e7343b7fd32085

05 Affected products

VendorProductVersionsPlatforms
ServiceNowNow Assist for CSM0 to < SR - CSM - Customer Service Management AI agent collection v6.1—

06 References