CVE-2026-5817
Docker Model Runner container-to-host code execution via unsandboxed trust_remote_code in Python inference backends
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 4.68.0
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- 2 proofs of concept on GitHub
CISA's decision points: whether it is exploited, whether attacks can be automated, and how much control an attacker gets. Assessed (SSVC 2.0.3).What do these mean? →
- Exploitation: none
- Automatable: no
- Technical impact: total
Summary
The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered. Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: none · Automatable: no · Technical impact: total
- Record last updated
Affected versions
- Docker Docker Desktop
From 4.62.0 · fixed in 4.68.0