THREATOPS
THREAT OPS › Threat News › [GHSA] GHSA-gq5q-89c7-vhvx (medium) — vLLM DeepSeek-OCR image processing vulnerable to denial of service

[GHSA] GHSA-gq5q-89c7-vhvx (medium) — vLLM DeepSeek-OCR image processing vulnerable to denial of service

medgithub_advisoriesPublished 2026-10-28

GHSA-gq5q-89c7-vhvx Severity: medium CVE: CVE-2026-115914

vLLM DeepSeek-OCR image processing vulnerable to denial of service

## Summary

Any vLLM deployment serving a model of the DeepSeek-OCR family — `deepseek-ai/DeepSeek-OCR`, `deepseek-ai/DeepSeek-OCR-2`, or `baidu/Unlimited-OCR` (whose `UnlimitedOCRForCausalLM` subclasses `DeepseekOCRForCausalLM`) — can be **killed by a single unauthenticat

Indicators of compromise

Original source: https://github.com/advisories/GHSA-gq5q-89c7-vhvx