Vllm: denials of service in vllm json web api
Key facts
- Attack vector
- Local
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Impact type
- Denial of service
- Confidentiality · integrity · availability
- None · None · High
- Fix status
- Partial Red Hat: 1 without a fix
Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-400.
Summary
A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| — | vllm | before 0.5.0.post1 | 0.5.0.post1 | Patch available | CNA |
| Red Hat | Red Hat Enterprise Linux AI (RHEL AI) | — | — | No fix listed | CNA |
| Red Hat | Red Hat Enterprise Linux AI (RHEL AI) | — | — | No fix listed | CNA |
| — | vllm (PyPI) | up to 0.5.0.post1 | — | No fix listed | GHSA-wc36-9694-f9rf |
- vllm Vendor— Affected before 0.5.0.post1 Fixed in 0.5.0.post1 Patch available CNA
- Red Hat Enterprise Linux AI (RHEL AI) VendorRed Hat Affected — Fixed in — No fix listed CNA
- Red Hat Enterprise Linux AI (RHEL AI) VendorRed Hat Affected — Fixed in — No fix listed CNA
- vllm (PyPI) Vendor— Affected up to 0.5.0.post1 Fixed in — No fix listed GHSA-wc36-9694-f9rf
Remediation
- Fix · CNA vllm Fixed in 0.5.0.post1
Vendor assessments
Red Hat
Red Hat rating: Moderate. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Red Hat Enterprise Linux AI (RHEL AI) | Affected | No fix planned: Will not fix |
Timeline
- 2026-10-02 Threatist record created from CVE-2024-8939
- 2026-10-03 Alias added: GHSA-wc36-9694-f9rf
References
More Red Hat vulnerabilities
- TI-2019-15875 Protection mechanism failure in Jenkins Pipeline: Groovy Plugin KEVCVSS 3.1CRITICAL 9.9
- TI-2019-15874 Protection mechanism failure in Jenkins Script Security Plugin KEVCVSS 3.1CRITICAL 9.9
- TI-2019-08259 Underflow in PHP-FPM can lead to RCE KEVCVSS 3.1CRITICAL 9.8
- TI-2019-05363 Code injection in Elastic Kibana KEVCVSS 3.1CRITICAL 10.0
- TI-2019-03949 Out-of-bounds write in ESXi and Horizon DaaS KEVCVSS 3.1CRITICAL 9.8
- TI-2018-16080 A code execution vulnerability exists in the Stapler web framework used by Jenkins 2.153… KEVCVSS 3.1CRITICAL 9.8
Sources
- CVE-2024-8939 · CVE Program
- CVE-2024-8939 · NVD
- FIRST EPSS
- GHSA-wc36-9694-f9rf · GitHub Advisory Database · CC BY 4.0
- CVE-2024-8939 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences