EUVD-2026-87748
GHSA-9fp6-6v59-w2jx
Severity by source
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/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
Network-reachable API with low complexity and a single crafted request; authenticated user required so PR:L; availability-only fatal EngineCore state gives A:H, no C/I impact and no scope change.
Primary rating from Vendor (VulnCheck).
CVSS VectorVendor: VulnCheck
Lifecycle Timeline
5DescriptionCVE.org
vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service).
Articles & Coverage 1
AnalysisAI
Denial of service in vLLM before 0.29.0 allows an authenticated API user to permanently disrupt the inference service with a single malformed request to the OpenAI-compatible POST /v1/completions or POST /v1/chat/completions endpoints. The server accepts user-supplied stop_token_ids and checks only that they are integers, not that they fall within the model's vocabulary/logits range; when min_tokens > 0 those ids are used as logits indices to suppress stop tokens, so an out-of-range value reaches a CUDA index_put_ operation and trips a device-side assertion that returns HTTP 500 and leaves EngineCore in a fatal state until the service is restarted. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
No credit card · 7-day full trial
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Requires an authenticated API user (PR:L) able to reach the OpenAI-compatible POST /v1/completions or POST /v1/chat/completions endpoints. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | This is a genuine but bounded availability risk. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | Full exploit scenario with step-by-step reproduction available after sign-in. |
| Remediation | Upgrade to vLLM 0.29.0 or later, which is the vendor-released fix for this issue; the GitHub advisory GHSA-v5gm-qgmv-gc6c confirms patch availability from the vendor, and the project is the authoritative source for the patched release artifact. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours, inventory all vLLM deployments and identify any running versions prior to 0.29.0, confirm exposure of the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints, and review API access logs for malformed stop_token_ids or HTTP 500 patterns; if immediate upgrade is not possible, restrict network access to these endpoints and limit API credentials. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Wazuh SIEM platform versions 4.4.0 through 4.9.0 contain an unsafe deserialization vulnerability in the DistributedAPI t
BentoML version 1.4.2 and earlier contains an unauthenticated remote code execution vulnerability through insecure deser
pgAdmin 4 contains critical remote code execution vulnerabilities in the Query Tool download and Cloud Deployment endpoi
The renderLocalView function in render/views.py in graphite-web in Graphite 0.9.5 through 0.9.10 uses the pickle Python
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Rated critica
OpenSSL before 0.9.8za, 1.0.0 before 1.0.0m, and 1.0.1 before 1.0.1h does not properly restrict processing of ChangeCiph
pyLoad download manager version prior to 0.5.0b3.dev77 exposes the Flask SECRET_KEY through an unauthenticated endpoint.
Langflow (a visual LLM pipeline builder) contains a critical unauthenticated code execution vulnerability (CVE-2026-3301
In Mercurial before 4.1.3, "hg serve --stdio" allows remote authenticated users to launch the Python debugger, and conse
Unauthenticated remote code execution affects Kestra OSS (the open-source event-driven orchestration platform) prior to
Unauthenticated remote code execution in Marimo ≤0.20.4 allows attackers to execute arbitrary system commands via the `/
pyLoad is the free and open-source Download Manager written in pure Python. Rated medium severity (CVSS 5.3), this vulne
Same weakness CWE-129 – Improper Validation of Array Index
View allSame technique Denial Of Service
View allVendor StatusVendor
Share
External POC / Exploit Code
Leaving vuln.today