Inference blocking via unrestricted ZeroMQ subscribers
Published Apr 30, 2025 · Updated Apr 30, 2025
Denial of service in vLLM Project vLLM 0.5.2 through 0.8.4 allows remote attackers to block inference via an exposed ZeroMQ socket. MessageQueue binds its XPUB socket to every interface and accepts unlimited subscribers, then can block while sending metadata to clients that do not read. Exploitation requires network access to the primary host during cross-host tensor parallelism; it can expose internal state and slow or stop publication.
Summary
What happened
Denial of service in vLLM Project vLLM 0.5.2 through 0.8.4 allows remote attackers to block inference via an exposed ZeroMQ socket. MessageQueue binds its XPUB socket to every interface and accepts unlimited subscribers, then can block while sending metadata to clients that do not read. Exploitation requires network access to the primary host during cross-host tensor parallelism; it can expose internal state and slow or stop publication.
The record
- CVE
- CVE-2025-30202
- Published
- Apr 30, 2025
- Updated
- Apr 30, 2025
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-770, T1499
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Apr 30, 2025CVE publishedPublication date reported by the CVE source.
- Apr 30, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=>= 0.5.2, < 0.8.5
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo