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.

Share this

Remediation#

Fixed upstream in vLLM 0.26.0.

Patch events

  1. This monthSecurity release

    AI toolingvLLM

    vLLM security release: 0.26.0

    Upgrade to 0.26.0

    Why: CVE-2026-73559: Public proof-of-concept exists (SSVC exploitation: poc).

Exploit intelligence#

SignalValueSource
Known exploitedNoCISA KEV
Ransomware use—CISA KEV
EPSS (30-day exploitation probability)0.4% (32th pct)FIRST EPSS v2026.06.15
CVSS base score4.3 (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 exploitationnoneCISA Vulnrichment
SSVC automatableNoCISA Vulnrichment
SSVC technical impactpartialCISA Vulnrichment

Affected versions (from the CVE record)#

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.

Elsewhere#

Distro status: Debian · Ubuntu · Red Hat · Alpine

Something wrong on this page?
Anonymous. Reports are checked against the primary source.

Also on today's list

See today's list → · Coming up →