vllm-project · vLLM · published 2026-08-17
CVE-2026-71486vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds
Routine No exploitation evidence; EPSS 0.4%.
CVE-2026-71486 is not known to be exploited in the wild. EPSS estimates a 0.4% chance of exploitation in the next 30 days, higher than 32% of all CVEs. This vLLM vulnerability: CVSS 4.3 (v3.1). Fixed upstream in vLLM 0.26.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.26.0.
Patch events
AI toolingvLLM
vLLM security release: 0.26.0
Upgrade to
0.26.0Why: CVE-2026-73559: Public proof-of-concept exists (SSVC exploitation: poc).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.4% (32th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 4.3 (v3.1)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
< 0.26.0(affected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.