Security readout for executives and security teams
Plain-English summary
CVE-2025-71379 affects vLLM deployments that process user-supplied model requests. Specially shaped inputs can make vulnerable regular expressions consume excessive CPU, slowing or denying service. This is a service availability issue, not described as data theft or code execution.
Executive priority
Prioritize remediation for internet-facing, customer-facing, or multi-tenant vLLM services. Treat as moderate business risk because it can disrupt AI service availability without evidence of data compromise or active exploitation.
Technical view
vLLM versions >= 0.6.3 and < 0.9.0 contain multiple CWE-1333 ReDoS flaws in LoRA utilities, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint. CVSS 4.0 is 5.3 with network attack vector, low complexity, low privileges, no user interaction, and low availability impact.
Likely exposure
Highest exposure is vLLM 0.6.3 through 0.8.x used in shared or user-facing inference services, especially OpenAI-compatible chat endpoints or workloads using phi4mini tool parsing or LoRA-related processing.
Exploitation context
The bundle reports crafted nested or repeated input can trigger catastrophic regex backtracking and severe CPU consumption. KEV is false, and no provided source states active exploitation.
Researcher notes
Evidence is limited to the CVE bundle, GHSA, and VulnCheck advisory. The bundle identifies affected version range and impacted components, but does not include exploit proof, active exploitation evidence, or detailed fixed commits.
Mitigation direction
- Upgrade affected vLLM deployments to version 0.9.0 or later.
- Review the GitHub advisory for vendor-specific remediation details.
- Limit access to vLLM inference endpoints to trusted authenticated users.
- Apply rate limiting and request size controls where supported.
- Monitor CPU saturation and inference latency for abnormal spikes.
Validation and detection
- Inventory vLLM versions across inference hosts and containers.
- Flag versions >= 0.6.3 and < 0.9.0 as vulnerable.
- Identify exposed OpenAI-compatible chat endpoints using vLLM.
- Check whether phi4mini parsing or LoRA utilities are enabled.
- Confirm upgraded systems report vLLM 0.9.0 or later.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-1333: Exact CWE lookup
Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupCVE-2025-71379 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Medium
- CVSS
- 5.3 (4.0)
- Known Exploited
- No
- Published
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
CVSS vector scores
2 official scoresWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N——VulnCheckCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L2.81.4VulnCheckVulnerability scoring details
Base CVSS 4.0 score
5.3MediumVector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N
Base CVSS 3.1 score
4.3MediumVector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
Source materials
- CVE List V5 sourceCVE List V5
- GHSA Advisory GHSA-j828-28rj-hfhpCVE reference, VulnCheck · vendor-advisory
- VulnCheck Advisory: vllm - Regular Expression Denial of Service in Multiple ComponentsCVE reference, VulnCheck · third-party-advisory
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Inefficient Regular Expression Complexity
Inefficient Regular Expression Complexity represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.