Description
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.
Metrics
CVSS 3.1 8.2/10
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:NWeakness enumeration
Affected software
No affected versions have been published.
Timeline
- Published
- May 12, 2026
- Last modified
- Jun 17, 2026
- NVD status
- Analyzed