# CVE-2026-59318: Spring AI tool calling privilege escalation

Source: https://junglewise.ai/threats/cve-2026-59318-spring-ai-tool-calling-privilege-escalation  
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-2026-59318 · Severity: medium · CVSS 6.5 · Published 2026-08-21

Spring AI, a framework for building AI-powered applications, has a flaw in how it enforces which tools (functions) are available to AI models in a given request. This allows an AI model to invoke tools that were not supposed to be available, potentially leading to privilege escalation and unauthorized access to sensitive functionality.

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

## Quick answers

**Is CVE-2026-59318 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-59318 being exploited in the wild.

**How severe is CVE-2026-59318?** Medium severity, with a CVSS score of 6.5, published 21 August 2026.

**Which products and versions are affected?** VMware Spring Ai 1.0.0 through 1.0.9, 1.1.0 through 1.1.8, 2.0.0.

**Is there a fix for CVE-2026-59318?** 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-2026-59318 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-59318?** Check whether you run VMware Spring Ai at an affected version. 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

In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked. This is a tool access control bypass vulnerability in the request handling layer. The vulnerability affects versions 1.0.0–1.0.9, 1.1.0–1.1.8, and 2.0.0. No evidence of active exploitation in the wild has been reported. Patches are expected from the Spring project.

## Affected products

- VMware Spring AI 1.0.0 through 1.0.9, 1.1.0 through 1.1.8, 2.0.0

## Timeline

- 2026-08-21: disclosed

## References

- [https://spring.io/security/cve-2026-59318](https://spring.io/security/cve-2026-59318)

## 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 Semantic Cache context hash isolation bypass](https://junglewise.ai/threats/cve-2026-59308-spring-ai-semantic-cache-context-hash-isolation-bypass)
- [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)