CVE-2026-41713
A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an uninte
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.
HIGH · CVSS 8.2
EPSS 0.00042
Schedule remediation
- SSVC automatable: yes - attacks can be scripted at scale
- CVSS base score ≥ 7.0
Sigma rules0
YARA rules0