CVE-2025-66448: vLLM vulnerable to remote code execution via transformers_utils/get_config
Noroxi assessment
Priority: Monitor (action score 35/100)
- 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: 0.70% (FIRST EPSS); higher than 53.9% of all records.
- Anyone who can reach it over the internet can trigger it. No account or password is required. A user must open a link or visit a page. No special conditions are required; it is repeatable.
- According to CISA the attack is automatable: targets can be found by mass scanning.
- Fixed version: vllm-project vllm 0.11.1.
Low priority for now. Upgrade to vllm-project vllm 0.11.1 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 (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.
- Published
- Dec 1, 2025
- Updated
- Oct 18, 2026
- EPSS
- 0.7% · 53th percentile
- CWE
- CWE-94
Report tools
Action score
35
Low priority for now.
- CVSS
- 35 / 40 · 8.8 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.7%
CISA SSVC decision
- Exploitation
- none
- Automatable
- yes
- Technical impact
- total
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- 8.8
- CNA · GitHub_M
- 7.1
- 1.7 point gap
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H
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.
Is your version affected? Check itNoroxi 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 helpAffected 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 |
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
- < 0.11.1affected
Affected versions
NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.
- vllm vllmbefore 0.11.1
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 0.11.1 | 0.11.1 |
Same product
vllm: all recordsOther highest-scoring records for the same primary product.
- CVE-2026-22778vLLM leaks a heap address when PIL throws an error60This week
- CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration40Plan
- CVE-2024-11041Remote Code Execution in vllm-project/vllm40Plan
Published before and after this one in the same product
- ← EarlierCVE-2025-62372Nov 21, 2025 · vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs33Monitor
- ← EarlierCVE-2025-62426Nov 21, 2025 · vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`26Monitor
- Later →CVE-2026-22773Jan 10, 2026 · vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions30Monitor
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 | 0.11.1 · description | Vendor (CNA) |
| PyPI:vllm | 0.11.1 | 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.
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2026-2280751 days apartvLLM affected by RCE via auto_map dynamic module loading during model initialization39Monitor
- CVE-2026-114053324 days apartvLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision36Monitor
- CVE-2026-90553285 days apartvLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor34Monitor
- CVE-2026-41523203 days apartvLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution30Monitor
Not on record for this CVE: EPSS history · researcher credit · public bounty program.
Technical details
Attack conditions
- Anyone who can reach it over the internet can trigger it.
- No account or password is required.
- A user must open a link or visit a page.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- high · data can be read
- Integrity
- high · data or configuration can be modified
- Availability
- high · the service can be disrupted
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- None
- User interaction
- Required
- Scope
- Unchanged
- Confidentiality impact
- High
- Integrity impact
- High
- Availability impact
- High
Weakness class (CWE)
CWE-94 · Improper Control of Generation of Code ('Code Injection')CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
nvd-primary
Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
Change log (1)
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
Show all references (2 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.