Description (CNA)
A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an unintended way. Applications using the affected advisor with user-controlled input may be susceptible to manipulation of model behavior across conversation turns.
Affected (CNA)
| Vendor / product | Versions |
|---|---|
| VMware / Spring AI | affected 1.0.0 before 1.0.7; affected 1.1.0 before 1.1.6 |
CWE
CWE-1336
References
- https://spring.io/security/cve-2026-41713
- https://nvd.nist.gov/vuln-metrics/cvss/v3-calculator?vector=AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N&version=3.1
ADP enrichment
No English description supplied.
No references supplied.