# CVE-2026-14890: SGLang remote code execution in expert-parallel backup subsystem

Source: https://junglewise.ai/threats/cve-2026-14890-sglang-remote-code-execution-in-expert-parallel-backup-subsystem  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-07-16. Updated: 2026-07-16  
License: CC BY 4.0 with a link back

CVE-2026-14890 · Severity: info · CVSS 9.8 · Published 2026-07-16

SGLang, a framework for serving large language models, contains a security vulnerability in its backup management component. An attacker can remotely execute unauthorized commands on the server because a network communication port lacks authentication and proper data validation. This could lead to a complete takeover of the AI serving infrastructure and exposure of sensitive model data.

Technologies: [SGLang Project SGLang](https://junglewise.ai/threats/technologies/sglang). Vendors: [SGLang Project](https://junglewise.ai/threats/vendors/sglang-project).

## Quick answers

**Is CVE-2026-14890 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-14890 being exploited in the wild.

**How severe is CVE-2026-14890?** Informational severity, with a CVSS score of 9.8, published 16 July 2026.

**Which products and versions are affected?** SGLang Project SGLang <= 0.5.14.

**Is there a fix for CVE-2026-14890?** 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-2026-14890 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-14890?** Check whether you run SGLang Project SGLang 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

SGLang (up to version 0.5.14) exposes a ZeroMQ PULL socket via its expert-parallel backup subsystem on a routable network interface. This socket lacks authentication and fails to implement deserialization safeguards when processing incoming data. An attacker can send a maliciously crafted Python pickle file to this port, leading to unauthenticated remote code execution (RCE). The vulnerability is present when the expert-parallel backup feature is enabled and the service is network-accessible. Security engineers should ensure the service is not exposed to untrusted networks and update to a patched version if available.

## Affected products

- SGLang Project SGLang <= 0.5.14

## Timeline

- 2026-07-16: disclosed: Initial disclosure via NVD and CERT/CC
- 2026-07-16: advisory

## References

- [http://vince.cert.org/vuls/id/326070](http://vince.cert.org/vuls/id/326070)
- [https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/elastic_ep/expert_backup_manager.py](https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/elastic_ep/expert_backup_manager.py)

## Related threats

- [SGLang uncontrolled memory allocation in Mooncake disaggregation backend](https://junglewise.ai/threats/cve-2026-112270-sglang-through-0-5-22-with-the-mooncake-disaggregation-backend)
- [SGLang Mooncake disaggregation backend unauthenticated denial of service](https://junglewise.ai/threats/cve-2026-112269-sglang-through-0-5-22-with-the-mooncake-disaggregation-backend)
- [SGLang server-side request forgery in prefill/decode disaggregation](https://junglewise.ai/threats/cve-2026-112267-sglang-through-0-5-22-in-prefill-decode-disaggregation-mode)
- [SGLang cache poisoning via untrusted mm_hashes in multimodal prefix cache](https://junglewise.ai/threats/cve-2026-111392-sglang-through-0-5-21-trusts-caller-supplied-mm-hashes-values-as)
- [SGLang code injection in _evaluate_filter()](https://junglewise.ai/threats/cve-2026-111391-sglang-0-5-10-through-0-5-22-contains-a-code-injection)