Eval Injection Affecting sglang package, versions [0,]
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-SGLANG-21692679
- published24 Oct 2026
- disclosed16 Oct 2026
- creditJiapeng Li, Jiajia Liu, Qiang Fu, Jiadai Wang
Introduced: 16 Oct 2026
NewCVE-2026-111391 (opens in a new tab)How to fix?
There is no fixed version for sglang.
Overview
sglang is a SGLang is a fast serving framework for large language models and vision language models.
Affected versions of this package are vulnerable to Eval Injection via _evaluate_filter(), which passes attacker-controlled input to eval(). A remote attacker can escape the eval() sandbox by exploiting re.search __globals__ access, enabling arbitrary Python code execution in the scheduler process on the next forward pass. The attack is delivered through the unauthenticated /dumper/configure endpoint by sending a filter expression that traverses the global namespace.
Note: This is only exploitable when DUMPER_SERVER_PORT is set.