CVE-2026-90713: vllm-project vLLM tiktoken vocab File mod.rs new denial of service
Noroxi assessment
Priority: Monitor (action score 7/100)
- 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: 0.16% (FIRST EPSS).
- Someone with local access to the system can trigger it. A low-privileged account is enough. No user action is required. No special conditions are required; it is repeatable.
- Fixed version: python-vllm (openSUSE:Tumbleweed) 0.30.0-1.1.
- Severity is disputed: the assigning authority (CNA) scores it 4.8, NVD 1.9.
Low priority for now. Upgrade to python-vllm (openSUSE:Tumbleweed) 0.30.0-1.1 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
A security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The attack is only possible with local access. The exploit has been released to the public and may be used for attacks. The pull request to fix this issue awaits acceptance.
- Published
- Sep 14, 2026
- Updated
- Sep 15, 2026
- EPSS
- 0.1% · 5th percentile
- CWE
- CWE-404
Report tools
Action score
7
Monitor
Low priority for now.
- CVSS
- 7 / 40 · 1.9 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.1%
CISA SSVC decision
- Exploitation
- proof of concept
- Automatable
- no
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- —
- CNA · VulDB
- 4.8
- NVD has not scored this yet; the score shown is the CNA’s.
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P
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.
—
Versions reported by the vendor
Affected version ranges reported by the assigning authority (VulDB). Independent of NVD's CPE analysis and usually ahead of it.
vllm-project vLLM
- 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.10, 0.11, 0.12 … (+17)affected
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| openSUSE:Tumbleweed | python-vllm | before 0.30.0-1.1 | 0.30.0-1.1 |
Same product
vllm-project: all recordsOther highest-scoring records for the same primary product.
- CVE-2024-9053Remote Code Execution in vllm-project/vllm39Monitor
- CVE-2026-114053vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision36Monitor
- CVE-2026-114055vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs34Monitor
Published before and after this one in the same product
- ← EarlierCVE-2026-9540May 26, 2026 · vllm-project vllm OpenAI-compatible Serving Path denial of service22Monitor
- ← EarlierCVE-2026-12491Jun 17, 2026 · Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations19Monitor
- Later →CVE-2026-90878Sep 15, 2026 · vllm-project vLLM Jinja Template Rendering completions resource consumption8Monitor
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 |
|---|---|---|
| opensuse:python-vllm | 0.30.0-1.1 · openSUSE:Tumbleweed | 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.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
- VulDB CNA Teamcoordinator
- Zyz3366 (VulDB User)reporter
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
- CVE-2026-9540111 days apartvllm-project vllm OpenAI-compatible Serving Path denial of service22Monitor
- CVE-2026-923652 days apartvllm-project vllm thinking_budget_state.py algorithmic complexity21Monitor
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
- Someone with local access to the system can trigger it.
- A low-privileged account is enough.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- Integrity
- Availability
- Attack vector
- Local
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
- Scope
- X
Weakness class (CWE)
CWE-404 · Improper Resource Shutdown or ReleaseCVSS vector
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P/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)
Change log
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
Show all references (7 more)Show less
Vendor advisories and official records. Exploit/PoC links are deliberately left out.