CVE-2026-22773
CVSS 6.5 Medium
- CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Published: 2026-01-10T07:16:03.527
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 1×1 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.
Related CVE by CWE
No related CWE found.
Top CVE for Vendor
No vendor taxonomy on this entry.
Recently Exploited Similar Vulnerabilities
No recent KEV-listed items for this vendor/product.
How to fix CVE-2026-22773
CVE-2026-22773 is a medium severity vulnerability affecting the affected product.
Description: 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 1×1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime […]
Exploit Difficulty: EASY
⏱️ Time to exploit: < 1 hour
🛠️ Required skills: Basic web security knowledge
💰 Public exploits: Likely available
How to Fix:
- Check if you're running the affected product
- Update to the latest patched version
- If patching is not immediately possible: restrict network exposure, apply least-privilege access
- Test the fix in a staging environment first
- Review logs for signs of exploitation
- Monitor for IOCs (Indicators of Compromise)
- Enable automatic security updates
- Set up vulnerability monitoring
- Review and harden security configurations
Description: 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 1×1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime […]
Exploit Difficulty: EASY
⏱️ Time to exploit: < 1 hour
🛠️ Required skills: Basic web security knowledge
💰 Public exploits: Likely available
How to Fix:
1 Identify affected systems
- Check if you're running the affected product
2 Immediate actions
- Update to the latest patched version
- If patching is not immediately possible: restrict network exposure, apply least-privilege access
3 Verification
- Test the fix in a staging environment first
- Review logs for signs of exploitation
- Monitor for IOCs (Indicators of Compromise)
4 Long-term prevention
- Enable automatic security updates
- Set up vulnerability monitoring
- Review and harden security configurations
Exploit Difficulty Assessment
EASY
Time to Exploit: < 1 hour
Skills Required: Basic web security knowledge
Public Exploits: Likely available
Vulnerability Timeline
Jan 10, 2026
Vulnerability Published
CVE details first published to NVD database
Jan 10, 2026
Imported to Database
Added to this CVE tracking system
Detection Rules & IOCs
No specific detection rules generated for this vulnerability type.
No vendor/product data available.