8.2
High
CVE-2026-41713 A malicious user could craft input that is stored in conversation memory and later interpreted by the model in an…
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 and versions
Other CVEs of Spring AI
The 5 CVEs of Spring AI →
CVE-2026-41712
Spring AI's chat memory component contained a problematic default that, when not explicitly overridden, could result…
7.5
High
CVE-2026-40966
In Spring AI, an attacker can bypass conversation isolation and exfiltrate sensitive memory from other users’ chat…
5.9
Medium
CVE-2026-22729
A JSONPath injection vulnerability in Spring AI's AbstractFilterExpressionConverter allows authenticated users to bypass…
8.6
High
CVE-2026-22730
A critical SQL injection vulnerability in Spring AI's MariaDBFilterExpressionConverter allows attackers to bypass…
8.8
High