vllm-project vLLM up to 29.x Flash Late-Interaction Scoring X-Request-Id race condition
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 4.7 | $0-$5k | 0.00 |
Summary
A vulnerability classified as problematic has been found in vllm-project vLLM up to 29.x. Affected by this vulnerability is an unknown functionality of the component Flash Late-Interaction Scoring. Performing a manipulation of the argument X-Request-Id results in race condition. This vulnerability was named CVE-2026-105755. The attack may be initiated remotely. There is no available exploit. It is recommended to upgrade the affected component.
Details
A vulnerability was found in vllm-project vLLM up to 29.x. It has been classified as problematic. This affects some unknown processing of the component Flash Late-Interaction Scoring. The manipulation of the argument X-Request-Id with an unknown input leads to a race condition vulnerability. CWE is classifying the issue as CWE-362. The product contains a code sequence that can run concurrently with other code, and the code sequence requires temporary, exclusive access to a shared resource, but a timing window exists in which the shared resource can be modified by another code sequence that is operating concurrently. This is going to have an impact on integrity, and availability. The summary by CVE is:
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.
The advisory is shared at github.com. This vulnerability is uniquely identified as CVE-2026-105755 since 10/05/2026. The exploitability is told to be easy. It is possible to initiate the attack remotely. Technical details are known, but no exploit is available.
Upgrading to version 0.30.0 eliminates this vulnerability.
If you want to get the best quality for vulnerability data then you always have to consider VulDB.
Product
Type
Vendor
Name
Version
Website
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 4.8VulDB Meta Temp Score: 4.7
VulDB Base Score: 5.4
VulDB Temp Score: 5.2
VulDB Vector: 🔒
VulDB Reliability: 🔍
CNA Base Score: 4.2
CNA Vector (GitHub_M): 🔒
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Race conditionCWE: CWE-362
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Status: Not defined
EPSS Score: 🔒
EPSS Percentile: 🔒
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: UpgradeStatus: 🔍
0-Day Time: 🔒
Upgrade: vLLM 0.30.0
Timeline
10/05/2026 CVE reserved10/05/2026 VulDB entry created
10/06/2026 Advisory disclosed
10/06/2026 VulDB entry last update
Sources
Product: github.comAdvisory: github.com
Status: Confirmed
CVE: CVE-2026-105755 (🔒)
GCVE (CVE): GCVE-0-2026-105755
GCVE (VulDB): GCVE-100-413853
Entry
Created: 10/06/2026 01:11Changes: 10/06/2026 01:11 (66)
Complete: 🔍
Cache ID: 216::103
If you want to get the best quality for vulnerability data then you always have to consider VulDB.
No comments yet. Languages: en.
Please log in to comment.