Spring AI at a glance
- Last 12 months
- 5
- Critical · all time
- 0
- Exploited · all time
- 0
- Public exploit · all time
- 1
Show as table
| Month | Vulnerabilities | Critical |
|---|---|---|
| Nov 2026 | 0 | 0 |
| Oct 2026 | 0 | 0 |
| Sep 2026 | 0 | 0 |
| Aug 2026 | 0 | 0 |
| Jul 2026 | 0 | 0 |
| Jun 2026 | 0 | 0 |
| May 2026 | 2 | 0 |
| Apr 2026 | 1 | 0 |
| Mar 2026 | 2 | 0 |
| Feb 2026 | 0 | 0 |
| Jan 2026 | 0 | 0 |
| Dec 2025 | 0 | 0 |
| Nov 2025 | 0 | 0 |
| Oct 2025 | 0 | 0 |
| Sep 2025 | 0 | 0 |
| Aug 2025 | 0 | 0 |
| Jul 2025 | 0 | 0 |
| Jun 2025 | 0 | 0 |
| May 2025 | 0 | 0 |
| Apr 2025 | 0 | 0 |
| Mar 2025 | 0 | 0 |
| Feb 2025 | 0 | 0 |
| Jan 2025 | 0 | 0 |
| Dec 2024 | 0 | 0 |
5 results · Feed
-
High 8.2
Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
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 co…
-
High 7.5
ChatMemory DEFAULT_CONVERSATION_ID causes unintended cross-user data leakage
Spring AI's chat memory component contained a problematic default that, when not explicitly overridden, could result in unintended data exposure between users.
-
Medium 5.9
VectorStoreChatMemoryAdvisor conversation scoping can lead to cross-tenant memory exfiltration
In Spring AI, an attacker can bypass conversation isolation and exfiltrate sensitive memory from other users’ chat histories, including secrets and credentials, by injecting filter logic through conversationId. Only applications that use VectorStoreChatMemory…
-
High 8.6
CVE-2026-22729: JSONPath Injection in Spring AI Vector Stores FilterExpressionConverter
A JSONPath injection vulnerability in Spring AI's AbstractFilterExpressionConverter allows authenticated users to bypass metadata-based access controls through crafted filter expressions. User-controlled input passed to FilterExpressionBuilder is concatenated…
-
High 8.8CVE-2026-22730 Public exploit
CVE-2026-22730: SQL Injection in Spring AI MariaDBFilterExpressionConverter
A critical SQL injection vulnerability in Spring AI's MariaDBFilterExpressionConverter allows attackers to bypass metadata-based access controls and execute arbitrary SQL commands. The vulnerability exists due to missing input sanitization.