AI / ML CVE-2026-22773
MEDIUM
GHSA-grg2-63fw-f2qr
Severity by source
AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Primary rating from GitHub Advisory.
CVSS VectorGitHub Advisory
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Lifecycle Timeline
4DescriptionGitHub Advisory
vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.
AnalysisAI
Vllm versions up to 0.12.0 is affected by allocation of resources without limits or throttling (CVSS 6.5).
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
Free forever · No credit card required
Vulnerability AssessmentAI
| Risk Assessment | CVSS 6.5 (MEDIUM). … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | An attacker could exploit this flaw, complete server termination. |
| Remediation | Fixed in version 0.12.0.. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 30 days: Identify affected systems running versions from 0.6.4 to and apply vendor patches as part of regular patch cycle. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Vendor StatusVendor
Share
External POC / Exploit Code
Leaving vuln.today