# CVE-2026-111391: SGLang code injection in _evaluate_filter()

Source: https://junglewise.ai/threats/cve-2026-111391-sglang-0-5-10-through-0-5-22-contains-a-code-injection  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-10-16. Updated: 2026-10-16  
License: CC BY 4.0 with a link back

CVE-2026-111391 · Severity: high · CVSS 8.1 · Published 2026-10-16

SGLang is a high-performance serving framework for large language models. Versions 0.5.10 through 0.5.22 contain a code injection vulnerability in the _evaluate_filter() function that allows unauthenticated remote attackers to execute arbitrary Python code on the scheduler process. An attacker can exploit this by sending a crafted filter expression to the /dumper/configure endpoint when the DUMPER_SERVER_PORT is enabled, gaining complete control over the LLM serving infrastructure.

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

## Quick answers

**Is CVE-2026-111391 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-111391 being exploited in the wild.

**How severe is CVE-2026-111391?** High severity, with a CVSS score of 8.1, published 16 October 2026.

**Which products and versions are affected?** SGLang Project SGLang 0.5.10 through 0.5.22.

**Is there a fix for CVE-2026-111391?** 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-2026-111391 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-111391?** 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

The vulnerability is a Python code injection in the _evaluate_filter() function that fails to properly sandbox eval() operations. An attacker can escape the eval() sandbox through re.search __globals__ to access and execute arbitrary Python code. The vulnerable /dumper/configure endpoint is unauthenticated and processes filter expressions on the next forward pass of the scheduler process.

## Affected products

- SGLang Project SGLang 0.5.10 through 0.5.22

## Timeline

- 2026-10-16: disclosed

## References

- [https://pypi.org/](https://pypi.org/)
- [https://github.com/sgl-project/sglang](https://github.com/sgl-project/sglang)

## 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 denial of service via disabled image decompression protection](https://junglewise.ai/threats/cve-2026-109229-sglang-through-0-5-21-contains-a-denial-of-service-vulnerability)