Code execution via implicit remote model trust
Published Jun 9, 2026 · Updated Jun 9, 2026
Code injection in InternLM LMDeploy 0.12.3 and earlier allows attackers to execute Python when a user loads a malicious model repository. The get_model_arch path and related loaders pass trust_remote_code=True to Hugging Face from_pretrained calls, which import repository-supplied configuration modules. Exploitation requires a user or pipeline to select an attacker-controlled repository; its top-level Python runs with the LMDeploy process user's permissions.
Summary
What happened
Code injection in InternLM LMDeploy 0.12.3 and earlier allows attackers to execute Python when a user loads a malicious model repository. The get_model_arch path and related loaders pass trust_remote_code=True to Hugging Face from_pretrained calls, which import repository-supplied configuration modules. Exploitation requires a user or pipeline to select an attacker-controlled repository; its top-level Python runs with the LMDeploy process user's permissions.
The record
- CVE
- CVE-2026-46517
- Published
- Jun 9, 2026
- Updated
- Jun 9, 2026
- Vendor
- InternLM
- Product
- LMDeploy
- Classifications
- CWE-915, CWE-94, CWE-1188, T1059.006
- Attack vector
- local
- Privileges
- unauthenticated
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
No public exploit references are available in this record.
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