vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids
Noroxi assessment
Priority: Monitor (action score 32/100)
- 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: 0.36% (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 0.24.0.
Low priority for now. Upgrade to vllm-project vllm 0.24.0 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 versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.
- Published
- Sep 26, 2026
- Updated
- Oct 6, 2026
- EPSS
- 0.3% · 28th percentile
- CWE
- CWE-20
Report tools
Action score
32
Monitor
Low priority for now.
- CVSS
- 32 / 40 · 8.2 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.3%
CISA SSVC decision
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · VulnCheck
- 8.2
- NVD has not scored this yet; the score shown is the CNA’s.
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
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 vllm0.22.0 and later · before 0.24.0
Versions reported by the vendor
Affected version ranges reported by the assigning authority (VulnCheck). Independent of NVD's CPE analysis and usually ahead of it.
vllm-project vllm
- 0.24.0not affected
- 0.22.0 and later · before 0.24.0affected · semver
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| PyPI | vllm | from 0.22.0 · before 0.24.0 | 0.24.0 |
Same product
vllm: all recordsOther highest-scoring records for the same primary product.
- CVE-2026-22778vLLM leaks a heap address when PIL throws an error44Plan
- CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration40Plan
- CVE-2024-11041Remote Code Execution in vllm-project/vllm40Plan
- CVE-2026-25960SSRF Protection Bypass in vLLM39Monitor
- CVE-2026-22807vLLM affected by RCE via auto_map dynamic module loading during model initialization39Monitor
- CVE-2025-47277vLLM Allows Remote Code Execution via PyNcclPipe Communication Service39Monitor
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 | 0.24.0 | Vendor (CNA) |
| PyPI:vllm | 0.24.0 | 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.
FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
No commit or PR link among the references.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
- rexpositoryreporter
- jperezdealgabacoordinator
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2025-62164310 days apartVLLM deserialization vulnerability leading to DoS and potential RCE35Monitor
- CVE-2026-5634098 days apartvLLM - Denial of Service via Unvalidated Multimodal Embeddings34Monitor
- CVE-2026-5423482 days apartvLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection30Monitor
- CVE-2026-34760177 days apartvLLM: Downmix Implementation Differences as Attack Vectors Against Audio AI Models28Monitor
- CVE-2026-1006470 days apartvLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt27Monitor
- CVE-2026-1057549 days apartvLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features26Monitor
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
- Integrity
- Availability
- Attack vector
- Network
- Attack complexity
- High
- Privileges required
- None
- User interaction
- None
- Scope
- X
Weakness class (CWE)
CWE-20 · Improper Input ValidationCVSS vector
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
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)
- Buffer Overflow via Environment VariablesCAPEC-10likelihood: High · High
- Server Side Include (SSI) InjectionCAPEC-101likelihood: High · High
- Cross Zone ScriptingCAPEC-104likelihood: Medium · High
- Command Line Execution through SQL InjectionCAPEC-108likelihood: Low · Very High
- Object Relational Mapping InjectionCAPEC-109likelihood: Low · High
- SQL Injection through SOAP Parameter TamperingCAPEC-110likelihood: High · Very High
- Double EncodingCAPEC-120likelihood: Low · Medium
- Subverting Environment Variable ValuesCAPEC-13likelihood: High · Very High
ATT&CK techniques
- Obfuscated Files or InformationT1027
- Masquerading: Invalid Code SignatureT1036.001
- Steal Web Session CookieT1539
- Subvert Trust Controls: Code SigningT1553.002
- Impair Defenses:Impair Command History LoggingT1562.003
- Hijack Execution Flow:Dynamic Linker HijackingT1574.006
- Hijack Execution Flow:Path Interception by PATH Environment VariableT1574.007
Change log
- Fix✗ → ✓
- SSVC exploitation— → none
For records you follow, these changes also arrive as notifications. →
References
Vendor advisories and official records. Exploit/PoC links are deliberately left out.