Code execution via unconditional remote-code trust
Published Jun 9, 2026 · Updated Jun 9, 2026
Code injection in InternLM LMDeploy 0.12.3 and earlier allows local users to execute Python code through a controlled model path. In lmdeploy/archs.py and lmdeploy/utils.py, model initialization passes that path to Hugging Face loaders with trust_remote_code=True, which downloads and imports repository-supplied Python. Exploitation requires control of the serving process's model path or deployment configuration and runs code with that process's privileges.
Summary
What happened
Code injection in InternLM LMDeploy 0.12.3 and earlier allows local users to execute Python code through a controlled model path. In lmdeploy/archs.py and lmdeploy/utils.py, model initialization passes that path to Hugging Face loaders with trust_remote_code=True, which downloads and imports repository-supplied Python. Exploitation requires control of the serving process's model path or deployment configuration and runs code with that process's privileges.
The record
- CVE
- CVE-2026-46432
- Published
- Jun 9, 2026
- Updated
- Jun 9, 2026
- Vendor
- InternLM
- Product
- LMDeploy
- Classifications
- CWE-94, T1059.006
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Jun 9, 2026CVE publishedPublication date reported by the CVE source.
- Jun 9, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=<= 0.12.3
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA local model-loading demonstrationproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo