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.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
VMware Spring AI
Default version status: unaffected
1.0.0 to < 1.0.7affected1.1.0 to < 1.1.6affected