Spring AI: Prompt Injection via Memory Poisoning in PromptChatMemoryAdvisor
CVE-2026-41713 · GHSA-5852-phmh-8fhr · published 2026-05-12 · updated 2026-05-18
- Severity
- High
- CVSS score
- 8.2
- Chance of exploitation (EPSS)
- 0.22%
- Fixed in
- 1.1.6
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Partial
- CISA SSVC
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.
Upgrade org.springframework.ai:spring-ai-client-chat to 1.1.6 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| org.springframework.ai:spring-ai-client-chat | Maven | < 1.0.7 | 1.0.7 |
| org.springframework.ai:spring-ai-client-chat | Maven | >= 1.1.0-M1, < 1.1.6 | 1.1.6 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- HighSpring AI: ChatMemory DEFAULT_CONVERSATION_ID causes unintended cross-user data leakageorg.springframework.ai:spring-ai-client-chat, org.springframework.ai:spring-ai-client-chat, org.springframework.ai:spring-ai-client-chat, org.springframework.ai:spring-ai-model, org.springframework.ai:spring-ai-model, org.springframework.ai:spring-ai-model
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.