High 8.1Published Oct 16, 2026

CVE-2026-111391SGLang 0.5.10 through 0.5.22 Code Injection via Debug Dumper Filter

Updated under an hour ago (Oct 28, 2026, 10:00 AM ET)

Does this affect you?

It affects sgl-project sglang. Add what you run to find out whether that includes you.

EPSS puts the chance of exploitation in the next 30 days at 0.45%, higher than 39% of scored CVEs.

Do this next

Start free and add your stack

Free account, 1 product

Every CVE for sgl-project sglang

Exploited in the last 30 days

SGLang 0.5.10 through 0.5.22 contains a code injection vulnerability in _evaluate_filter() that allows remote attackers to execute Python code by escaping the eval() sandbox through re.search __globals__. Attackers can send a crafted filter expression to the unauthenticated /dumper/configure endpoint when DUMPER_SERVER_PORT is set, running code in the scheduler process on the next forward pass.

CVSS: 8.1 HIGH (v3.1, CNA)CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness (CWE): CWE-95
Known exploited: Not in CISA's KEV catalog
EPSS (exploitation in the next 30 days): 0.45% (percentile 39)
Assigned by: VulnCheck
NVD analysis: Deferred
Record last updated: Oct 16, 2026
First seen by InfoSec Signals: Oct 16, 2026

Affected products

Affected products

sgl-project sglang sgl_project:sglang (from the name)	from 0.5.10 through 0.5.22	CNA record

References

References

https://github.com/sgl-project/sglang/issues/44188	issue-tracking
https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/debug_utils/dumper.py#L1309-L1320	technical-description
https://github.com/sgl-project/sglang/blob/v0.5.22/python/sglang/srt/debug_utils/dumper.py#L1380-L1401	technical-description
https://github.com/sgl-project/sglang	product
https://www.vulncheck.com/advisories/sglang-0.5.10-through-0.5.22-code-injection-via-debug-dumper-filter	third-party-advisory

The CVE record on cve.org NVD's entry

The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.