CVE-2026-47155: vLLM: Artifact Pin Decay in vLLM allows pinned deployments to load unpinned code, weights, and processors
Noroxi assessment
Priority: Monitor (action score 26/100)
- 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: 0.24% (FIRST EPSS).
- Anyone who can reach it over the internet can trigger it. No account or password is required. No user action is required. Special conditions such as timing or configuration are required.
- Fixed version: vllm-project vllm 0.22.0.
Low priority for now. Upgrade to vllm-project vllm 0.22.0 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 (LLMs). Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.
- Published
- Jun 22, 2026
- Updated
- Oct 25, 2026
- EPSS
- 0.2% · 16th percentile
- CWE
- CWE-345
Report tools
Action score
26
Monitor
Low priority for now.
- CVSS
- 26 / 40 · 6.5 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.2%
CISA SSVC decision
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · GitHub_M
- 6.5
- 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
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 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 |
Affected versions
NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.
- vllm vllmbefore 0.22.0
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
- < 0.22.0affected
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 0.22.0 | 0.22.0 |
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-2026-56340Jun 20, 2026 · vLLM - Denial of Service via Unvalidated Multimodal Embeddings34Monitor
- ← EarlierCVE-2026-41523Jun 22, 2026 · vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution30Monitor
- Later →CVE-2026-48746Jun 22, 2026 · vLLM: OpenAI auth bypass36Monitor
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 | 0.22.0 · description | Vendor (CNA) |
| PyPI:vllm | 0.22.0 | 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.
No history yet (it accumulates with the daily EPSS job).
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 researchersFinders, 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.
No nightly-computed relations.
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.
- No account or password is required.
- No user action is required.
- Special conditions such as timing or configuration are required.
If successful
- Confidentiality
- low · data can be read
- Integrity
- high · data or configuration can be modified
- Availability
- none
- Attack vector
- Network
- Attack complexity
- High
- Privileges required
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality impact
- Low
- Integrity impact
- High
- Availability impact
- None
Weakness class (CWE)
CWE-345 · Insufficient Verification of Data AuthenticityCVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N
nvd-secondary
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)
- JSON Hijacking (aka JavaScript Hijacking)CAPEC-111likelihood: High · High
- Cache PoisoningCAPEC-141likelihood: High · High
- DNS Cache PoisoningCAPEC-142likelihood: High · High
- Content SpoofingCAPEC-148likelihood: Medium · Medium
- Spoofing of UDDI/ebXML MessagesCAPEC-218Medium
- Application API Message Manipulation via Man-in-the-MiddleCAPEC-384Low
- Transaction or Event Tampering via Application API ManipulationCAPEC-385Medium
- Application API Navigation RemappingCAPEC-386Medium
Change log
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
Show all references (3 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.