Service interruption via catastrophic regex backtracking
Published Jun 20, 2026 · Updated Jun 20, 2026
Regular expression denial of service in vLLM 0.6.3 and later before 0.9.0 allows remote attackers to interrupt service via crafted input. Patterns in vllm/lora/utils.py, the Phi-4-mini tool parser, and the chat endpoint perform unbounded backtracking on nested or repeated input. Network access to an affected API is sufficient to drive excessive CPU use and degrade or halt request processing.
Summary
What happened
Regular expression denial of service in vLLM 0.6.3 and later before 0.9.0 allows remote attackers to interrupt service via crafted input. Patterns in vllm/lora/utils.py, the Phi-4-mini tool parser, and the chat endpoint perform unbounded backtracking on nested or repeated input. Network access to an affected API is sufficient to drive excessive CPU use and degrade or halt request processing.
The record
- CVE
- CVE-2025-71379
- Published
- Jun 20, 2026
- Updated
- Jun 20, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- T1499.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 20, 2026CVE publishedPublication date reported by the CVE source.
- Jun 20, 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=0.6.3 <0.9.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
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