Unauthenticated code execution via unsafe pickle deserialization
Published Sep 9, 2025 · Updated Sep 10, 2025
Unsafe deserialization in SGLang 0.4.6 allows remote attackers to execute arbitrary code through a crafted weight-update request. The /update_weights_from_tensor path base64-decodes serialized_named_tensors and passes the bytes to ForkingPickler.loads without restricting loadable classes. The HTTP endpoint must be network-reachable, and successful exploitation runs code with the SGLang server process's permissions.
Summary
What happened
Unsafe deserialization in SGLang 0.4.6 allows remote attackers to execute arbitrary code through a crafted weight-update request. The /update_weights_from_tensor path base64-decodes serialized_named_tensors and passes the bytes to ForkingPickler.loads without restricting loadable classes. The HTTP endpoint must be network-reachable, and successful exploitation runs code with the SGLang server process's permissions.
The record
- CVE
- CVE-2025-10164
- Published
- Sep 9, 2025
- Updated
- Sep 10, 2025
- Vendor
- SGLang
- Product
- SGLang
- Classifications
- CWE-502, CWE-20, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 9, 2025CVE publishedPublication date reported by the CVE source.
- Sep 10, 2025Record 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=0.4.6
What conditions does exploitation require?
What is affected?
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