vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds
Summary
| CVE | CVE-2026-71486 |
|---|---|
| State | PUBLISHED |
| Assigner | GitHub_M |
| Source Priority | CVE Program / NVD first with legacy fallback |
| Published | 2026-08-17 20:16:45 UTC |
| Updated | 2026-08-18 13:17:29 UTC |
| Description | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0. |
Risk And Classification
Primary CVSS: v3.1 4.3 MEDIUM from [email protected]
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
EPSS: 0.003410000 probability, percentile 0.271560000 (date 2026-08-18)
Problem Types: CWE-400 | CWE-770 | CWE-400 CWE-400: Uncontrolled Resource Consumption | CWE-770 CWE-770: Allocation of Resources Without Limits or Throttling
| Version | Source | Type | Score | Severity | Vector |
|---|---|---|---|---|---|
| 3.1 | [email protected] | Secondary | 4.3 | MEDIUM | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L |
| 3.1 | CNA | DECLARED | 4.3 | MEDIUM | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L |
CVSS v3.1 Breakdown
Attack Vector
NetworkAttack Complexity
LowPrivileges Required
LowUser Interaction
NoneScope
UnchangedConfidentiality
NoneIntegrity
NoneAvailability
LowCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
Vendor Declared Affected Products
| Source | Vendor | Product | Version | Platforms |
|---|---|---|---|---|
| CNA | Vllm-project | Vllm | affected < 0.26.0 | Not specified |
References
| Reference | Source | Link | Tags |
|---|---|---|---|
| github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8... | [email protected] | github.com | |
| github.com/vllm-project/vllm/pull/47260 | [email protected] | github.com | |
| github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff | [email protected] | github.com | |
| github.com/vllm-project/vllm/releases/tag/v0.26.0 | [email protected] | github.com | |
| CVE Program record | CVE.ORG | www.cve.org | canonical |
| NVD vulnerability detail | NVD | nvd.nist.gov | canonical, analysis |
No vendor comments have been submitted for this CVE.
There are currently no legacy QID mappings associated with this CVE.