HighVulnerability
CVE-2026-0596: mlflow command injection through model_uri when serving with enable_mlserver
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-0596
- Published
- Record updated
- Affected
- mlflow < 3.9.0
- Fixed in
- 3.9.0
- released January 29, 2026, 61 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 1.3%
Summary
CVE-2026-0596 is a command injection flaw in mlflow/mlflow when serving a model with `enable_mlserver=True`. The `model_uri` is embedded directly into a shell command run via `bash -c` without sanitization, so shell metacharacters such as `$()` or backticks enable command substitution and attacker-controlled command execution. The issue affects the latest version of mlflow/mlflow and can lead to privilege escalation if a higher-privileged service serves models from a directory writable by lower-privileged users.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Affected packages in the Exposure Registry
Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.
- mlflowPyPILLM dependency since 2024-05-30 · 17 tracked dependents
Related items
- MediumCVE-2026-128136: NLTK pickle loading lets crafted models read or truncate local filesSimilar attack · NVD/CVE Database
- HighCVE-2026-76818: Axon rtkx bootstrap runs unverified downloaded binarySimilar attack · NVD/CVE Database
- MediumMicrosoft’s Agent Framework PyPI package compromised to steal credentialsSimilar attack · BleepingComputer
- InfoOX Security Launches OX Radar and Response Center to Show Companies Which Cyber Threats Actually Affect ThemSimilar attack · CSO Online
- MediumCVE-2026-132122: agentic-radar untrusted .env loading leaks OpenAI API key via scan commandSimilar attack · NVD/CVE Database