Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-92972 – Unauthenticated Route Poisoning / KV Metadata Exposure – SGLang ≤ 0.5.19 (Prefill/D

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-92972 is a missing authentication vulnerability (CWE-306) in SGLang, an open-source LLM serving framework, affecting deployments that run in prefill/decode disaggregation mode. An unauthenticated PUT /route endpoint on the prefill bootstrap service allows a remote attacker to poison the KV transfer routing table, redirecting decode workers to attacker-controlled endpoints. The flaw is rated High severity and is remotely exploitable without authentication or user interaction.

Technical details

  • Root cause: the prefill bootstrap service in SGLang exposes a PUT /route endpoint with no authentication or access control on a function that modifies critical routing state.
  • The endpoint accepts attacker-supplied rank_ip and rank_port values, which are written into the KV transfer routing table used to coordinate prefill/decode disaggregation.
  • Trigger condition: the target must be running SGLang in prefill/decode disaggregation mode with the prefill bootstrap service reachable over the network.
  • Attack vector: network-based, no privileges or user interaction required.
  • Impact: an attacker can redirect decode workers to attacker-controlled endpoints, resulting in denial of service to the inference service and potential disclosure of KV transfer metadata (e.g., session identifiers and tensor-parallel topology parameters).

Affected software

  • sgl-project SGLang, versions 0 through 0.5.19 (when running in prefill/decode disaggregation mode)

Severity

  • CVSS v3.1 Base Score: 8.6 (High) — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H
  • CVSS v4.0 Base Score: 8.8 (High) — CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:H/SC:N/SI:N/SA:N

Mitigation and recommended actions

  • Immediate: No patched version has been identified in the advisory at time of publication. Monitor the official SGLang repository for a fix and upgrade as soon as one is released.
  • Network mitigation: Restrict network access to the prefill bootstrap service and its /route endpoint so it is not reachable from untrusted networks (e.g., internal/private network only, firewall or security-group rules).
  • Workaround: Where possible, avoid exposing prefill/decode disaggregation mode services directly to the internet; place them behind an authenticating proxy or network segmentation until an upstream authentication mechanism is available.
  • Detection: Monitor for unexpected modifications to the KV transfer routing table and unusual rank_ip/rank_port values or connections from unfamiliar hosts.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge