CVE-2026-71486: vllm · Uncontrolled Resource Consumption
Affects vllmSource CVE Database V5
Not known to be exploited · CVSS 4.3 Medium : upgrade to 0.26.0 when convenient.
Data as of 15 Nov 2026, 20:25 UTC
- EPSS
- 0.3% chance of exploitation in 30 days – higher than 31% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 0.26.0
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:LExploitation evidence
Disclosed: evidence found.
CVE published 17 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 15 Nov 2026.
What to do
Upgrade vllm to 0.26.0.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| vllm-projectvllm | Affected
| Fixed in
|
PyPIvllmpkg:pypi/vllmOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
If you cannot patch yet, restrict access to the derender endpoints to trusted clients only and monitor usage patterns for unusually large or complex derender requests. Implementing rate limiting or input validation on the size of token ID lists before processing could mitigate exploitation risk.
Description
CVE-2026-71486 is a medium severity vulnerability in vllm-project vllm versions prior to 0.26.0. It affects the /v1/completions/derender and /v1/chat/completions/derender API endpoints, which accept client-supplied generated output data without enforcing limits on token counts or response sizes. This allows an authenticated API client to cause uncontrolled CPU and memory consumption proportional to the size of the attacker-supplied token data, bypassing normal generation output bounds.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff (opens in a new tab)
- github.com/vllm-project/vllm/pull/47260 (opens in a new tab)
- github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b (opens in a new tab)
- github.com/vllm-project/vllm/releases/tag/v0.26.0 (opens in a new tab)