CVE-2026-111391— SGLang 0.5.10 through 0.5.22 Code Injection via Debug Dumper Filter
Quick assessment
Affected
sgl-project sglang
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.
SGLang 0.5.10 至 0.5.22 版本在 函数中存在代码注入漏洞。攻击者可利用该漏洞，通过 的 属性逃逸 沙箱，从而执行任意 Python 代码。当启用了 配置时，攻击者可向未认证的 端点发送特制的过滤表达式，进而在下一次前向传播过程中于调度器进程中执行恶意代码。
Possible ATT&CK Techniques 3 AI
T1055 · Process Injection T1059.006 · Python T1190 · Exploit Public-Facing ApplicationAffected Version Matrix 1
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| sgl-project | sglang | 0.5.10≤ 0.5.22 |
affected |
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2026-111391
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
SGLang 0.5.10 through 0.5.22 Code Injection via Debug Dumper Filter
Source: CVE Program / CVE List V5
Vulnerability Description
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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
动态执行代码中指令转义处理不恰当(Eval注入)
Source: CVE Program / CVE List V5
Affected Products
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| sgl-project | sglang | 0.5.10 ~ 0.5.22 | - |
|
II. Public POCs for CVE-2026-111391
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-111391
请登录查看更多情报信息。
Vendor Advisories for CVE-2026-111391 (1)
Proof of Concept for CVE-2026-111391 (1)
Other References for CVE-2026-111391 (1)
IV. Related Vulnerabilities
Same product: sglang
-
CVE-2026-111392
SGLang through 0.5.21 KV Cache Poisoning via mm_hashes in /g -
CVE-2026-110809
sgl-project SGLang Session Cleanup session_controller.py Ses -
CVE-2026-110807
sgl-project SGLang generate Endpoint io_struct.py denial of -
CVE-2026-109229
SGLang through 0.5.21 Decompression Bomb DoS via NanoNemotro -
CVE-2026-109228
SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video
Same vendor: sgl-project
-
CVE-2026-111392
SGLang through 0.5.21 KV Cache Poisoning via mm_hashes in /g -
CVE-2026-110809
sgl-project SGLang Session Cleanup session_controller.py Ses -
CVE-2026-110807
sgl-project SGLang generate Endpoint io_struct.py denial of -
CVE-2026-109229
SGLang through 0.5.21 Decompression Bomb DoS via NanoNemotro -
CVE-2026-109228
SGLang through 0.5.21 Resource Budget Bypass via GLM-V Video
Same weakness: CWE-95
-
CVE-2026-111865
THU-MIG yoloe AutoBackend Model Loading autobackend.py eval -
CVE-2026-111687
WeRSS (we-mp-rss) through 1.5.3 RCE via template Parameter i -
CVE-2026-111237
Ultralytics FastSAM AutoBackend Model Loading autobackend.py -
CVE-2026-111212
ImprintLab Medical-SAM-Adapter AutoBackend Model Loading aut -
CVE-2026-86002
Dokku: Host Command Execution via eval of Unsanitized Docker
V. Comments for CVE-2026-111391
No comments yet