Evidence used
- No CISA KEV confirmation is currently recorded.
- EPSS is 0.66% for the current model date.
BlackTreeCVE IntelligenceFull vulnerability report · 2025
CVE-2025-66448High confidence
vLLM vulnerable to remote code execution via transformers_utils/get_config
vllm-project · vllm
Official source article: GitHub GHSA-8FR4-5Q9J-M8GM ↗. Check the applicable product and release in the original source.
7.1HighCVSS 3.1
Within 7 days
Patch availableHigh technical severity; prioritise exposed affected systems while verifying vendor guidance.
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 the affected network interface to trusted sources where business-safe.
- 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.
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 |
|---|---|---|---|
| pipvllm | < 0.11.1 | 0.11.1 | GitHub advisory ↗upstream repository advisory · 17 Jul 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-2025-66448 · CSAF 2.0 · revision 3 · finalRed Hat Product Securityvllm: vLLM: Remote Code Execution via malicious model configuration
The vendor explicitly identifies these products as affected by this CVE.
- rhelai1/bootc-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-aws-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-azure-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-azure-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-gcp-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-intel-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/instructlab-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/instructlab-intel-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/instructlab-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- 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
- Summary
- A remote code execution vulnerability has been identified in vLLM. An attacker can exploit a weakness in the model loading process to silently fetch and run unauthorized, malicious Python code on the host system. This happens because the engine mistakenly executes code from a remote repository referenced in a model's configuration, even when explicit security measures are set to prevent it.
- Remediation
- For more information visit https://access.redhat.com/errata/RHSA-2025:23080
High technical severity; prioritise exposed affected systems while verifying vendor guidance.
Patch available01
What, why and how
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.
What
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.
Why
Untrusted data can cross into a code-evaluation path and be interpreted as executable instructions.
How
An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may execute code or commands in the affected security context.
What
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.
Why
Untrusted data can cross into a code-evaluation path and be interpreted as executable instructions.
How
An attacker operating through a network path may attempt exploitation with low privileges. 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
- a network path → Improper Control of Generation of Code ('Code Injection') → execute code or commands in the affected security context
- Attack surface
- Network
- Privileges required
- Low: a basic authenticated account is required
- User interaction
- Required interaction required
- Attack complexity
- High: exploitation depends on specific conditions
- 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-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:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:HCommon 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.ACHighAttack complexity: Successful exploitation depends on specific conditions outside the attacker's direct control.PRLowPrivileges required: The attacker needs basic user-level privileges.UIRequiredUser interaction: Another user must perform an action for exploitation to succeed.SUnchangedScope: The security impact remains within the vulnerable component's authority.CHighConfidentiality impact: A successful attack can cause a major loss.IHighIntegrity impact: A successful attack can cause a major loss.AHighAvailability impact: A successful attack can cause a major loss.- 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. - Patch available
- Affected
- rhelai1/bootc-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-aws-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-azure-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-azure-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-gcp-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-intel-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/bootc-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/instructlab-amd-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/instructlab-intel-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- rhelai1/instructlab-nvidia-rhel9 as a component of Red Hat Enterprise Linux AI (RHEL AI)
- 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-cuda-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
- rhoai/odh-vllm-cuda-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- rhoai/odh-vllm-rocm-rhel9 as a component of Red Hat OpenShift AI (RHOAI)
- Fixed
- registry.redhat.io/rhaiis/model-opt-cuda-rhel9@sha256:14e32e88f1b89f59ed34a6d712746b82a6a54c6ed4727784f18aeff853abbdc7_arm64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/model-opt-cuda-rhel9@sha256:dce6b0ea03379bf06664a5200af8b5f5ae3fad13cdce6d21873843f22554800b_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:7b04c0154c486aa7dd103ddeaf6bea7b9851859c33a4b979a85261a44a7b77f2_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:bddcf7ab6d576572b6d60822c313ffebcd9869e4fde93e32ac327821f93cf32b_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:dcb9d1cd005c40b6db6f893e56419e383b9dcc0d38315605cb1457e2af5354f7_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:ec961e5acfde5c1ad0a7e0e2c86a0bf56b9bc46357fa124f9db6dff1006076ab_arm64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:f0ab1b678e9447eae4b6b2fe5c58531aa8524133db157f196726164e4dc20492_arm64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-cuda-rhel9@sha256:fa844e16d06e871f1a5dbc2fd5b3882d28112eee8d6bee601d94c96295c5e24f_arm64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-rocm-rhel9@sha256:53007894763e03f609c35c727cb738db3c2130b19fa0e1069c24240e0870fb7a_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-rocm-rhel9@sha256:7856bdb7ae0d643a7b9362c164d4d4fe3c0c7186f5fff73a7ae9835b3df52e57_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-rocm-rhel9@sha256:c5efe40fa2a6e98d7d3d6676befff0dbbd87b2887769bb7e5856c5b0b0ada125_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-rocm-rhel9@sha256:e3b3efcdd86f60b90664a249d45918b2ac5f45bae5eed5399e310d63e878b287_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-tpu-rhel9@sha256:64796b48c68d31973a08e22c9530c39b1bc3ba9f376bbefa57643ef0fc857534_amd64 as a component of Red Hat AI Inference Server 3.2
- registry.redhat.io/rhaiis/vllm-spyre-rhel9@sha256:681d191e22994e4da2d4844219e2401ee363d4b3524cd19bb00076dce685a36a_s390x as a component of Red Hat AI Inference Server 3.3
- registry.redhat.io/rhaiis/vllm-spyre-rhel9@sha256:906987407c1ed10139dadc5f8aef64584f407a6017467fce726e2e9c42d9f9c8_amd64 as a component of Red Hat AI Inference Server 3.3
- registry.redhat.io/rhaiis/vllm-spyre-rhel9@sha256:9c8187509c26e824143f51f9522d7b6457f3aea33e5f7983bb203e4bb231473d_ppc64le as a component of Red Hat AI Inference Server 3.3
- registry.redhat.io/rhoai/odh-vllm-cpu-rhel9@sha256:10ea60405654199ff5d09b50fc8b83f6d9bb9dda8057e18441dead800b8fa974_ppc64le as a component of Red Hat OpenShift AI 2.25
- registry.redhat.io/rhoai/odh-vllm-cpu-rhel9@sha256:5ee020fd12200f51352e83ee3936ef0a00ade392ef3ce3deace5109354962b66_s390x as a component of Red Hat OpenShift AI 2.25
- registry.redhat.io/rhoai/odh-kserve-agent-rhel9@sha256:1f2995ee9de8b0dd7e45fc26dcef5f5a7a2e38b2e564ab3e6460c4af76e22e82_arm64 as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-agent-rhel9@sha256:599c13b4ecdaf8cfe00bef9270d5ef4286c4f5a238bacf801f901973b152c694_ppc64le as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-agent-rhel9@sha256:8a8b9aa606fadb92796dc1310c4604c669570da12735fe73f73b65386c439556_s390x as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-agent-rhel9@sha256:fe135e808533f7267267fe2f6bfcba0f28d2184991d82ccd1b85eab6b815c3c9_amd64 as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:67dee2abb1b3db82eeafba21914fdb5904ce09b95f2888dea485a5a7df4d58e6_amd64 as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:861d9c9ff292c8baf9f541a384ab323943c1d0aec29349dde7ac957d2dde7ee7_ppc64le as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:9c240f185478ac30dd82c9b55c0a882a45744c08a6f698da754872b0eeb9103e_arm64 as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-controller-rhel9@sha256:afb0fb167b488bb53706e2979bd58b4ee88f2624642b76dccc3a7e3f7ab0aa7e_s390x as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-router-rhel9@sha256:25306815d697653646bda1a84d7efc28403e1c62b3bb8a144319854ad527771d_arm64 as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-router-rhel9@sha256:4fb1f0d669a402cfeb3b7c241a1a095a245c004d553807eb1760bda41c697d9e_amd64 as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-router-rhel9@sha256:a0e6b5b5133598ee3aa52b2047889105269d90467dea0541885ce3ee07e90235_ppc64le as a component of Red Hat OpenShift AI 3.3
- registry.redhat.io/rhoai/odh-kserve-router-rhel9@sha256:b54a836af6a4837a3bbb95e2575ef5d33a380af9e18fcda29b005d654c1149a1_s390x as a component of Red Hat OpenShift AI 3.3
- and 7 more
- Action
- For more information visit https://access.redhat.com/errata/RHSA-2025:23080
- Workaround
- No verified workaround is recorded. If business-safe, reduce exposure to the affected interface and allow only trusted sources until authoritative guidance is available.
04
Evidence and provenance
Published 1 Dec 2025 · Last source change 2 Dec 2025, 14:14 UTC · CWE-94 · Improper Control of Generation of Code ('Code Injection')
CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source FIRST · tracked since 2026-08-14
?
The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.European sourceENISA EUVD · EUVD-2025-200115
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
- Affected versionsThe structured affected or fixed version information changed.Red Hat Product Security ↗
- Before
- < 0.11.1 · Fixed: An authoritative update reference is available, but the fixed version is not recorded in the structured CVE fields. Check the linked vendor advisory for the applicable release.
- After
- < 0.11.1 · Fixed: For more information visit https://access.redhat.com/errata/RHSA-2025:23080
CVE published
Fixed release or patch reference recorded
Fixed release recorded from official guidance
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.