Worker crash via unbounded audio decompression
Published Sep 16, 2026 · Updated Sep 18, 2026
Resource exhaustion in vLLM before 0.24.0 allows remote attackers to crash inference workers through compressed chat audio. The /v1/chat/completions input_audio path calls AudioMediaIO.load_bytes or load_file without supplying the configured decode-duration limit, so a small file expands into a large float32 PCM allocation. Exposure requires an audio-capable model and a reachable chat endpoint; default deployments lack authentication, and exploitation interrupts worker availability.
Summary
What happened
Resource exhaustion in vLLM before 0.24.0 allows remote attackers to crash inference workers through compressed chat audio. The /v1/chat/completions input_audio path calls AudioMediaIO.load_bytes or load_file without supplying the configured decode-duration limit, so a small file expands into a large float32 PCM allocation. Exposure requires an audio-capable model and a reachable chat endpoint; default deployments lack authentication, and exploitation interrupts worker availability.
The record
- CVE
- CVE-2026-57173
- Published
- Sep 16, 2026
- Updated
- Sep 18, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-770, T1499.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 16, 2026CVE publishedPublication date reported by the CVE source.
- Sep 18, 2026Record 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=< 0.24.0
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.
Activity data is delayed. The latest report is Sep 28, 2026.
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
Get started to see how Hinoki identifies affected software and validates exploitability in your environment.
Get started