vllm: Inefficient Regular Expression Complexity
CVE-2025-71379 is a high-severity inefficient regular expression complexity vulnerability in vllm, with a CVSS 3.1 base score of 7.5 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. The record lists version 0.9.0 as the first without the flaw, so updating vllm to that release or later removes the exposure. There is no confirmed exploitation so far. EPSS estimates a 0.48% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Update vllm to 0.9.0 or a later version.
- Read the advisory on github.com for workarounds and exact fixed builds.
- Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
Affected products and versions
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- NoneNo data is disclosed.
- Integrity
- NoneNothing can be modified.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H. Scored by NVD.
| Scoring system | Score | Severity | Scored by |
|---|---|---|---|
| CVSS 4.0 | 5.3 | Medium | CNA (vulncheck.com) |
| CVSS 3.1 | 4.3 | Medium | CNA (vulncheck.com) |
| CVSS 3.1 | 7.5 | High | NVD |
Official description
vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Inefficient Regular Expression Complexity
The product uses a regular expression with a worst-case computational complexity that is inefficient and possibly exponential.
How developers prevent this class of flaw
- Use regular expressions that do not support backtracking, e.g. by removing nested quantifiers.
- Set backtracking limits in the configuration of the regular expression implementation, such as PHP's pcre.backtrack_limit. Also consider limits on execution time for the process.
- Do not use regular expressions with untrusted input. If regular expressions must be used, avoid using backtracking in the expression.
More Inefficient Regular Expression Complexity vulnerabilities (CWE-1333)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: partial).
- Record last changed materially (score, affected products, status or references).
References
Advisories
Third-party and government advisories
Other vulnerabilities in vllm
- 7.5 High severity
- 7.5 High severity
- 7.5 High severity
- 9.8 Critical severity
Recent Inefficient Regular Expression Complexity vulnerabilities
- 7.5 High severity
- 8.7 High severity
- 7.5 High severity
- 7.5 High severity
- 7.5 High severity
- 7.5 High severity
Spotted an error? Tell us.