CVE-2026-112268: Incorrect Authorization in sgl-project sglang-router
Description
sglang-router versions up to 0.3.2 have an authorization bypass vulnerability allowing users with data-plane API keys to access high-availability (HA) management routes without proper admin role checks. This enables unauthorized reading of cluster topology, modification of gossiped configuration, adjustment of global rate limits, and silent shutdown of HA coordination.
CVSS v4.0
Score 5.3medium
Affected software
sgl-project
sglang-router
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
Technical Analysis
CVE-2026-112268 describes an authorization bypass in sglang-router (sgl-model-gateway) through version 0.3.2. The vulnerability arises because the /ha/* endpoints do not enforce control-plane Admin role checks, allowing holders of data-plane API keys to access these endpoints improperly. Exploitation permits reading cluster topology, writing configuration data, changing global rate limits, and invoking POST /ha/shutdown to disrupt HA coordination silently.
Potential Impact
Attackers with data-plane API keys can bypass intended authorization controls to access sensitive HA management functionality. This can lead to unauthorized disclosure of cluster topology, unauthorized configuration changes, manipulation of rate limits, and disruption of HA coordination by shutting down HA services without detection.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict issuance and use of data-plane API keys to trusted entities only and monitor for unusual access patterns to /ha/* endpoints.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-10-19T13:25:26.666Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6ad623792cdf04f6565c8807
Added to database: 10/19/2026, 14:04:41 UTC
Last enriched: 10/19/2026, 14:18:59 UTC
Last updated: 10/19/2026, 14:19:15 UTC
Views: 5
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
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
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.