Evidence used
- No CISA KEV confirmation is currently recorded.
- EPSS is 0.31% for the current model date.
BlackTreeCVE IntelligenceFull vulnerability report · 2026
CVE-2026-90553High confidence
vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor
vllm-project · vLLM
Official source article: GitHub GHSA-3C86-2M5G-59Q7 ↗. Check the applicable product and release in the original source.
8.5HighCVSS 4.0
Patch only the product branches with a verified fix
Fix availability varies by productHigh technical severity; 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 severityHigh→Operational priority:High, unchanged from published severity.unchanged
Compensating controls
- Validate the affected product branch and deploy the verified fixed release.
- Restrict local access and enforce least privilege on affected hosts.
- Monitor vendor guidance and exploitation sources for a material change.
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 ranges1 source-attributed range
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 0.28.0 | 0.28.0 | OSV record ↗source linked ecosystem record · 17 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-2026-90553 · CSAF 2.0 · revision 3 · finalRed Hat Product Securityvllm: vLLM: Remote Code Execution via LlavaOnevision2 processor ignoring trust_remote_code
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. The LlavaOnevision2 processor loader incorrectly ignores the `trust_remote_code` parameter, which is designed to prevent the execution of untrusted code. This oversight allows an attacker to craft a malicious model containing arbitrary code. When such a model is loaded, the code executes with the vLLM process's authority, leading to remote code execution.
- Remediation
- To mitigate this issue, ensure that only trusted models are loaded into vLLM instances. This operational control helps prevent the execution of arbitrary code, even when the `trust_remote_code` parameter is bypassed.
High technical severity; 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 before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.
What
vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.
Why
Untrusted data can cross into a code-evaluation path and be interpreted as executable instructions.
How
An attacker operating through local access may attempt exploitation when the stated preconditions are met. If successful, the issue may execute code or commands in the affected security context.
What
vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.
Why
Untrusted data can cross into a code-evaluation path and be interpreted as executable instructions.
How
An attacker operating through local access may attempt exploitation when the stated preconditions are met. If successful, the issue may execute code or commands in the affected security context.
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 None recorded
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.
- Likely attack path
- local access → Improper Control of Generation of Code ('Code Injection') → execute code or commands in the affected security context
- Attack surface
- Local
- Privileges required
- None: unauthenticated exploitation is possible
- User interaction
- Passive interaction required
- Attack complexity
- Low: no specialised conditions are recorded
- Security boundary
- Not a CVSS 4.0 base metric
- Weakness
?
CWE means Common Weakness Enumeration: a standard category for the underlying weakness. - CWE-94 ↗
CWE-94: Improper Control of Generation of Code ('Code Injection'). The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.
- CVSS vector
?
CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity. CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NCommon Vulnerability Scoring System 4.0: the compact vector below is decoded into plain language.
AVLocalAttack vector: The attacker needs local access to the vulnerable system.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.ATNoneAttack requirements: No additional deployment or execution condition is required.PRNonePrivileges required: The attacker does not need an account or existing privileges.UIPassiveUser interaction: A user must unknowingly interact with the vulnerable system.VCHighVulnerable-system confidentiality: A successful attack can cause a major loss.VIHighVulnerable-system integrity: A successful attack can cause a major loss.VAHighVulnerable-system availability: A successful attack can cause a major loss.SCNoneSubsequent-system confidentiality: No direct loss is represented by this metric.SINoneSubsequent-system integrity: No direct loss is represented by this metric.SANoneSubsequent-system availability: No direct loss is represented by this metric.- Post-exploitation / living off the land
- After compromise, an attacker may use built-in shells, scripting engines, scheduled tasks and native network utilities for discovery, persistence or movement. This is a plausible LoTL path, not evidence that it has occurred for every attack.
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
- vLLM: 0.28.0
- 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
- To mitigate this issue, ensure that only trusted models are loaded into vLLM instances. This operational control helps prevent the execution of arbitrary code, even when the `trust_remote_code` parameter is bypassed.
Official vendor articles1 stored document
Linked articles are downloaded and versioned as source evidence. A CVE mention or approved update relationship does not, by itself, verify a fix for every product branch.
- LlavaOnevision2 processor loader executes attacker model code with `trust_remote_code=False` (inert `trust_remote_code` kwarg to `transformers.get_class_from_dynamic_module`) — RCE from a malicious model · Advisory · vllm-project/vllm · GitHub →Original publisher ↗Searchable text snapshot · Captured 26 Sep 2026vllm-project / vllm Public Uh oh! There was an error while loading. Please reload this page . Notifications You must be signed in to change notification settings Fork 22.7k Star 92.7k Code Issues 2.5k Pull requests 5k+ Discussions Actions Projects Security and quality 83 Insights Additional navigation
04
Evidence and provenance
Published 12 Sept 2026 · Last source change 14 Sept 2026, 18:25 UTC · CWE-94 · Improper Control of Generation of Code ('Code Injection')
CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source FIRST · tracked since 2026-09-14
?
The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.European sourceENISA EUVD · EUVD-2026-76871
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 from remediation: access.redhat.com/CVE-2026-90553 to remediation: access.redhat.com/CVE-2026-90553.Red Hat Product Security ↗
- Before
- remediation: access.redhat.com/CVE-2026-90553
- After
- remediation: access.redhat.com/CVE-2026-90553
- Remediation statusRemediation status changed from Awaiting fix to Mitigation available.Red Hat Product Security ↗
- Before
- Awaiting fix
- After
- Mitigation available
- Vendor guidanceAuthoritative vendor guidance changed: added vendor advisory: github.com/GHSA-3c86-2m5g-59q7.disclosure@vulncheck.com ↗
- Before
- remediation: github.com/GHSA-3c86-2m5g-59q7
- After
- remediation: github.com/GHSA-3c86-2m5g-59q7 · vendor advisory: github.com/GHSA-3c86-2m5g-59q7
- ENISA EUVD mappingEUVD-2026-76871 was added to the official ENISA EUVD mapping for this CVE.ENISA EUVD ↗
- Before
- not recorded
- After
- {"euvdId":"EUVD-2026-76871"}
- Catalogue recordCVE added to the BlackTree catalogue.CNA ↗
CVE published
Fixed release or patch reference recorded
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.