Evidence used
- No CISA KEV confirmation is currently recorded.
- A structured source references public exploit or proof-of-concept material.
- EPSS is 0.37% for the current model date.
BlackTreeCVE IntelligenceFull vulnerability report · 2026
CVE-2026-71486High confidence
vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds
vllm-project · vllm
Official source article: GitHub GHSA-8737-QX52-HJFF ↗. Check the applicable product and release in the original source.
4.3MediumCVSS 3.1
Patch only the product branches with a verified fix
Fix availability varies by productMedium technical severity with public exploit material referenced by a structured source; prioritise exposed affected systems while verifying vendor guidance. Verified remediation exists for at least one product or source, but 27 structured product or package states remain unresolved. Apply remediation only to the exact product branch confirmed by its source.
R
Open reassessment dashboard →Operational reassessment
Published severity in operational context
Published severityMedium→Operational priority:High, raised one band.upgradedsince 18 Aug 2026
Compensating controls
- Validate the affected product branch and deploy the verified fixed release.
- Restrict the affected network interface to trusted sources where business-safe.
- Increase monitoring for the attack path and post-exploitation behaviour described in the report.
Verification
- Confirm that the asset runs vllm-project vllm and falls inside the recorded affected range.
- Verify the installed build against the product-specific fixed version after deployment.
- Validate exposure, authentication requirements and compensating controls in the actual environment.
- Reopen this reassessment when CVSS, KEV, EPSS, exploit evidence or remediation changes.
Remediation availability differs by product scope
Verified remediation exists for at least one product or source, but 27 structured product or package states remain unresolved. Apply remediation only to the exact product branch confirmed by its source.
- Red Hat Product Security: 27 affected or under-investigation product states without a fixed product state in the same current advisory
Open-source package ranges3 source-attributed ranges
These OSV and GitHub advisory ranges apply only to the named package and ecosystem. A listed fixed version is not a universal product patch or proof that an update is installed.
| Ecosystem and package | Affected range | First fixed version | Evidence |
|---|---|---|---|
| PyPIvllm | ECOSYSTEM: introduced 0; fixed 0.26.0 | 0.26.0 | OSV record ↗aggregator derived · 10 Sep 2026 |
| PyPIvllm | ECOSYSTEM: introduced 0; fixed 0.26.0 | 0.26.0 | OSV record ↗source linked ecosystem record · 10 Sep 2026 |
| pipvllm | < 0.26.0 | 0.26.0 | GitHub advisory ↗upstream repository advisory · 4 Sep 2026 |
Direct vendor intelligence
1 currentAuthoritative vendor CSAF and VEX advisories
Structured product status and remediation from the issuing vendor. Product-state explanations are always visible; large lists can be searched or downloaded.
CVE-2026-71486 · CSAF 2.0 · revision 3 · finalRed Hat Product Securityvllm: vLLM: Denial of Service via unbounded token ID decoding
The vendor explicitly identifies these products as affected by this CVE.
- rhaii/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-gaudi-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-rocm-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-spyre-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-rocm-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-spyre-rhel9 as a component of Red Hat AI Inference Server
- Summary
- A flaw was found in vLLM. An authenticated API client can exploit derender endpoints by providing oversized GenerateResponse objects. These endpoints process the objects without enforcing output bounds or response-size limits. This can lead to excessive consumption of CPU and memory resources, resulting in a Denial of Service (DoS).
- Remediation
- Fix deferred
Medium technical severity with public exploit material referenced by a structured source; prioritise exposed affected systems while verifying vendor guidance. Verified remediation exists for at least one product or source, but 27 structured product or package states remain unresolved. Apply remediation only to the exact product branch confirmed by its source.
Fix availability varies by product01
What, why and how
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.
What
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.
Why
The product does not properly control the allocation and maintenance of a limited resource.
How
An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.
What
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.
Why
The product does not properly control the allocation and maintenance of a limited resource.
How
An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.
02
Exploit reality and attack path
CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.
Observed exploitation No confirmed evidence
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.
Public PoC / exploit material Reference recorded
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.A structured CVE source labels at least one public reference as exploit material. BlackTree has not independently validated that it is safe, reliable or weaponised.
- Likely attack path
- a network path → Uncontrolled Resource Consumption → cause the confidentiality, integrity or availability impact described by the vendor
- Attack surface
- Network
- Privileges required
- Low: a basic authenticated account is required
- User interaction
- None
- Attack complexity
- Low: no specialised conditions are recorded
- Security boundary
- Unchanged: impact remains within the vulnerable component's security authority
- Weakness
?
CWE means Common Weakness Enumeration: a standard category for the underlying weakness. - CWE-400 ↗
CWE-400: Uncontrolled Resource Consumption. The product does not properly control the allocation and maintenance of a limited resource.
- CVSS vector
?
CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity. CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:LCommon Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.
AVNetworkAttack vector: The vulnerable component can be reached over a network.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.PRLowPrivileges required: The attacker needs basic user-level privileges.UINoneUser interaction: No action by another user is required.SUnchangedScope: The security impact remains within the vulnerable component's authority.CNoneConfidentiality impact: No direct loss is represented by this metric.INoneIntegrity impact: No direct loss is represented by this metric.ALowAvailability impact: A successful attack can cause a limited loss.- Post-exploitation / living off the land
- Stolen credentials, tokens and legitimate administration functions may provide continued access without deploying a large custom toolset.
03
Patch and workaround
Operational remediation based on structured source evidence.
- Status
?
Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change. - Fix availability varies by product
- Affected
- rhaii/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-gaudi-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-rocm-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-spyre-rhel9 as a component of Red Hat AI Inference Server
- rhaii/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-neuron-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-rocm-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-spyre-rhel9 as a component of Red Hat AI Inference Server
- rhaiis/vllm-tpu-rhel9 as a component of Red Hat AI Inference Server
- rhelai3/bootc-aws-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
- rhelai3/bootc-azure-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
- rhelai3/bootc-azure-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
- rhelai3/bootc-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
- rhelai3/bootc-gaudi-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
- rhelai3/bootc-gcp-cuda-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
- rhelai3/bootc-rocm-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI) 3
- rhoai/odh-kserve-agent-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- rhoai/odh-kserve-controller-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- rhoai/odh-kserve-router-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- rhoai/odh-kserve-storage-initializer-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- rhoai/odh-llm-d-kv-cache-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- rhoai/odh-th-torch-cuda-py312-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- rhoai/odh-vllm-gaudi-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- Fixed
- 0.26.0.
- Action
- Use the product-specific evidence above. Patch only products with a verified fixed release, and keep every affected or under-investigation state without a matching fix in the remediation queue.
- Workaround
- A mitigation or workaround reference is available from the source linked below; validate it against the affected product and version.
04
Evidence and provenance
Published 17 Aug 2026 · Last source change 18 Aug 2026, 12:34 UTC · CWE-400 · Uncontrolled Resource Consumption
CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source FIRST · tracked since 2026-08-23
?
The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.European sourceENISA EUVD · EUVD-2026-60376
Product sourceVendor CSAF · Red Hat Product Security
Remediation sourceVendor CSAF · Red Hat Product Security
CWE sourceCNA
NVD statusNVD enriched
Core structured fields are present and their contributing authorities are shown above.
Material change intelligence
View recent updates ↗What changed after publication
- Vendor guidanceAuthoritative vendor guidance changed: added mitigation: github.com/GHSA-8737-qx52-hjff; added patch: github.com/47260; removed remediation: github.com/GHSA-8737-qx52-hjff; 2 further additions.security-advisories@github.com ↗
- Before
- remediation: github.com/GHSA-8737-qx52-hjff
- After
- mitigation: github.com/GHSA-8737-qx52-hjff · patch: github.com/47260 · patch: github.com/8e61b646e2d157f9b93451fa048f9c8530c8a67b · 1 more references
- Affected versionsThe structured affected or fixed version information changed.CNA ↗
- Before
- < 0.26.0 · Fixed: 0.26.0.
- After
- vllm: < 0.26.0 · Fixed: 0.26.0.
- Public exploit evidencePublic exploit evidence changed from No public exploit to Public exploit reference.security-advisories@github.com ↗
- Before
- No public exploit
- After
- Public exploit reference
- Catalogue recordCVE added to the BlackTree catalogue.CNA ↗
- Vendor guidanceAuthoritative vendor guidance changed: added remediation: github.com/GHSA-8737-qx52-hjff; removed remediation: github.com/8e61b646e2d157f9b93451fa048f9c8530c8a67b.CNA ↗
- Before
- remediation: github.com/8e61b646e2d157f9b93451fa048f9c8530c8a67b
- After
- remediation: github.com/GHSA-8737-qx52-hjff
Technical terms and abbreviations used in this report
- CVE
- Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
- CVSS
- Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
- EPSS
- Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
- CWE
- Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
- CNA
- CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
- CISA ADP
- Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
- NVD
- National Vulnerability Database: NIST's enrichment service for CVE records.
- CERT / CSIRT
- A computer security incident response team that publishes warnings or coordinates incident response.
- PoC
- Proof of concept: public material that demonstrates or helps reproduce exploitation.
- CSAF
- Common Security Advisory Framework: a machine-readable format for security advisories.
- LoTL
- Living off the land: abuse of legitimate tools or system functions during an attack.