NVD / CVE Program· CNA GitHub_M

CVE-2026-71486: vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds

Noroxi assessment

Priority: Monitor (action score 17/100)

The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
Probability of exploitation in the next 30 days: 0.37% (FIRST EPSS).
Anyone who can reach it over the internet can trigger it. A low-privileged account is enough. No user action is required. No special conditions are required; it is repeatable.
Fixed version: vllm-project vllm 0.26.0.

Low priority for now. Upgrade to vllm-project vllm 0.26.0 or later.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

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.

MediumCVSS 4.3 · v3.1—No exploit Fix available

Denial of service

Published: Aug 17, 2026
Updated: Oct 23, 2026
EPSS: 0.3% · 31th percentile
CWE: CWE-400

Report tools

JSON

Action score

Monitor

Low priority for now.

CVSS: 17 / 40 · 4.3 / 10
CISA KEV: 0 / 30 · Not listed
EPSS: 0 / 30 · 0.3%

CISA SSVC decision

Exploitation: none
Automatable: no
Technical impact: partial

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD: —
CNA · GitHub_M: 4.3; NVD has not scored this yet; the score shown is the CNA’s.

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

Not in KEV: no record of exploitation in the wild
No public exploit code on record
A fix has been released

If any of these changes, we'll tell you in the daily email digest.

Running WordPress? Scan your site free with WP Lens

Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

Vendor	Product	CPE
vllm	vllm	cpe:2.3:a:vllm:vllm

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

vllm vllmbefore 0.26.0

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

vllm-project vllm
- < 0.26.0affected

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

Ecosystem	Package	Affected range	Fix
PyPI	vllm	before 0.26.0	0.26.0

Same product

vllm: all records

Other highest-scoring records for the same primary product.

CVE-2026-22778vLLM leaks a heap address when PIL throws an error
60This week
CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration
40Plan
CVE-2024-11041Remote Code Execution in vllm-project/vllm
40Plan

Published before and after this one in the same product

← EarlierCVE-2026-73558Aug 13, 2026 · vLLM: Cross-User Data Leak Vulnerability
21Monitor
← EarlierCVE-2026-73559Aug 13, 2026 · vLLM: Completion prompt lists fan out into unbounded engine requests
26Monitor
Later →CVE-2026-73560Aug 17, 2026 · vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
26Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

Product / package	Fixed version	Source
vllm-project vllm	0.26.0 · description	Vendor (CNA)
PyPI:vllm	0.26.0	Package registry (OSV)

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

No dated events beyond publication.

EPSS, last 120 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

No credits in the CNA record.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

CVE-2026-11617769 days apartvLLM 0.10.2 before 0.25.0 DoS via Nemotron-VL Processor Decompression-Bomb Guard Bypass
34Monitor
CVE-2026-3723711 days apartvLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion.
30Monitor
CVE-2026-10575949 days apartvLLM: Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens in the vLLM Rust frontend metrics middleware (unauthenticated denial of
30Monitor
CVE-2026-549767 days apartUnbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm
30Monitor
CVE-2025-48956361 days apartvLLM API endpoints vulnerable to Denial of Service Attacks
30Monitor
CVE-2026-10065140 days apartvllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass
28Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

—

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

Technical details

Attack conditions

Anyone who can reach it over the internet can trigger it.
A low-privileged account is enough.
No user action is required.
No special conditions are required; it is repeatable.

If successful

Confidentiality: none
Integrity: none
Availability: low · the service can be disrupted

Attack vector: Network
Attack complexity: Low
Privileges required: Low
User interaction: None
Scope: Unchanged
Confidentiality impact: None
Integrity impact: None
Availability impact: Low

Weakness class (CWE)

CWE-400 · Uncontrolled Resource Consumption

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L

nvd-secondary

Root cause

Code that parses nested structures sets no depth or size limit. A small input can turn into a disproportionate processing load.

The bug in code

The whole CWE-400 class

A representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.

Vulnerable

1function expand(node) {
2  return node.children.map(expand);
3}

Fixed

1const MAX_DEPTH = 32;
2function expand(node, depth = 0) {
3  if (depth > MAX_DEPTH) throw new Error("too deep");
4  return node.children.map((c) => expand(c, depth + 1));
5}