Hostile Inference: Exploiting Docker Model Runner for Container Escapes
Local LLM inference is seeing adoption in default developer workflows, and the tooling that serves those models now ships inside products developers already trust. One of those is Docker Model Runner (DMR), the feature in Docker Desktop that pulls, runs, and serves models locally. In November 2025, we reported ZDI-26-150 / CVE-2026-28400 , a denial-of-service (on macOS) stemming from an unauthenticated argument-injection vulnerability in DMR. A container created with the default set of privileges could overwrite and corrupt the Docker Desktop VM’s data disk. Further analysis, under non-default configurations, turned the same primitive into arbitrary code execution on the host, on both macOS
Read at Zero Day Initiative blog
- Vendor
- Apple, Docker
- Product
- macOS, Docker Desktop / Engine
- Exposure class
- Operating system, Developer platform
Why it ranks 27 (Notable)
- Product class: operating system, developer platform
- Widely deployed vendor product (Apple)
- Covered by 2 independent sources
- Threat research
- Recency: items published within 24 hours gain 15, within 72 hours 6, within 7 days 2.
Links
- Zero Day Initiative blog (thezdi.com)
- CVE-2026-28400 on this site · NVD · CVE.org · Vulnpedia
- CVE-2024-8695 on this site · NVD · CVE.org · Vulnpedia
- CVE-2024-8696 on this site · NVD · CVE.org · Vulnpedia
- CVE-2024-6222 on this site · NVD · CVE.org · Vulnpedia
- CVE-2025-9074 on this site · NVD · CVE.org · Vulnpedia
Related coverage
Other items that share a CVE or were clustered with this one.