Skip to main content

CVE-2026-93838: Allocation of Resources Without Limits or Throttling in sgl-project sglang

0
High
Published: 09/18/2026 (09/18/2026, 21:32:27 UTC)
Source: CVE Database V5
Vendor/Project: sgl-project
Product: sglang

Description

SGLang versions through 0.5.20 contain an unbounded memory allocation vulnerability in handle_staging_req() that fails to validate chunk_idx from ZMQ STAGING_REQ frames in prefill/decode disaggregation deployments. Attackers with access to the decode engine's internal ZMQ rank port can send a frame with an extremely large chunk_idx value, causing the scheduler to allocate memory until the system runs out and terminates the process.

CVSS v4.0

Score 8.2high

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
Present
Privileges Required
None
User Interaction
None
Vuln. Confidentiality
None
Vuln. Integrity
None
Vuln. Availability
High
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Affected software

sgl-project

sglang

Affected versions
>=0 <=0.5.20
sglang
pkg:pypi/sglang
Affected versions
>=0 <=0.5.20

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/18/2026, 19:46:43 UTC

Technical Analysis

CVE-2026-93838 describes an unbounded memory allocation vulnerability in SGLang versions through 0.5.20. The issue exists in the handle_staging_req() function, which fails to validate the chunk_idx field from ZMQ STAGING_REQ frames used in prefill/decode disaggregation deployments. An attacker with access to the decode engine's internal ZMQ rank port can send a frame with an extremely large chunk_idx value, causing the scheduler to allocate excessive memory until the system runs out of resources and the process is terminated.

Potential Impact

Successful exploitation results in denial of service due to resource exhaustion, as the process handling the decode engine will terminate when memory is depleted. There is no indication of privilege escalation or data compromise from the provided information.

Mitigation Recommendations

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict access to the decode engine's internal ZMQ rank port to trusted entities only to prevent unauthorized exploitation.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulnCheck
Date Reserved
2026-09-18T18:16:36.587Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6aad91cb55bf5e2cf571918f

Added to database: 09/18/2026, 19:32:27 UTC

Last enriched: 09/18/2026, 19:46:43 UTC

Last updated: 09/19/2026, 01:33:44 UTC

Views: 6

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses