CVE-2026-22778

Summary

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.

Affected Software

VendorProductVersion RangeStatus
vllm-projectvllm>= 0.8.3, < 0.14.1affected

Weaknesses

  • CWE-532: CWE-532: Insertion of Sensitive Information into Log File

ADP Enrichment

CISA ADP Vulnrichment

  • SSVC:
  • Exploitation: none
    • Automatable: yes
    • Technical Impact: total

vLLM: vLLM: Remote code execution via invalid image processing in the multimodal endpoint.

Additional References

References