# CVE-2026-59308: Spring AI Semantic Cache context hash isolation bypass

Source: https://junglewise.ai/threats/cve-2026-59308-spring-ai-semantic-cache-context-hash-isolation-bypass  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-08-21. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-59308 · Severity: medium · CVSS 4.2 · Published 2026-08-21

Spring AI is a framework for building AI-powered applications that includes a Semantic Cache feature to optimize performance by reusing previous AI responses. A flaw in how the cache isolates responses between different system prompts allows cached results from one context to be inappropriately returned for unrelated contexts, potentially exposing incorrect or sensitive information across different use cases.

Technologies: [VMware Spring Ai](https://junglewise.ai/threats/technologies/spring-ai). Vendors: [VMware](https://junglewise.ai/threats/vendors/vmware).

## Quick answers

**Is CVE-2026-59308 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-59308 being exploited in the wild.

**How severe is CVE-2026-59308?** Medium severity, with a CVSS score of 4.2, published 21 August 2026.

**Which products and versions are affected?** Pivotal Spring AI 2.0.0.

**Is there a fix for CVE-2026-59308?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-59308 attacked?** It is attacked over the network.

**Am I affected by CVE-2026-59308?** Check whether you run VMware Spring Ai. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

The vulnerability is a context isolation bypass in Spring AI's Semantic Cache implementation. The context hash algorithm used to segregate cached responses based on system prompts is insufficient, allowing responses cached for one system prompt to be retrieved and served in unrelated contexts with different system prompts. This is a logical flaw in the cache key derivation rather than a cryptographic weakness. An attacker does not require authentication or network-level access beyond normal application use; they simply need to interact with the cached AI system in a way that triggers retrieval of responses from a different context. The impact is information disclosure—a user could receive AI-generated responses that were cached for a different system prompt, potentially revealing sensitive context or instructions. Patches are available in versions after 2.0.0.

## Affected products

- Pivotal Spring AI 2.0.0

## Timeline

- 2026-08-21: disclosed

## References

- [https://spring.io/security/cve-2026-59308](https://spring.io/security/cve-2026-59308)

## Related threats

- [Spring AI RedisChatMemoryRepository RediSearch injection in findByMetadata()](https://junglewise.ai/threats/cve-2026-59319-spring-ai-redischatmemoryrepository-redisearch-injection-in)
- [Spring AI path traversal in ResourceCacheService](https://junglewise.ai/threats/cve-2026-59294-spring-ai-path-traversal-in-resourcecacheservice)
- [Spring AI tool calling privilege escalation](https://junglewise.ai/threats/cve-2026-59318-spring-ai-tool-calling-privilege-escalation)
- [Spring AI unbounded session accumulation denial of service](https://junglewise.ai/threats/cve-2026-59279-spring-ai-unbounded-session-accumulation-denial-of-service)
- [VMware Spring AI query injection in Vector Stores](https://junglewise.ai/threats/cve-2026-47835-vmware-spring-ai-query-injection-in-vector-stores)