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.
Add your gear to cvedb and we'll alert you only when vmware ships something exploited.
Check my exposure →This product uses data from the NVD API but is not endorsed or certified by the NVD. Informational only; not professional security advice.