Authenticated code execution via unverified pickle deserialization
Published May 14, 2026 · Updated May 14, 2026
Unsafe deserialization in Amazon SageMaker Python SDK allows remote authenticated users to execute code in inference containers. The Triton inference handler loads pickle-based model artifacts from S3 without verifying their integrity, so a replaced artifact executes automatically at the next container lifecycle event. Exploitation requires ModelBuilder with Triton and S3 write access to the model artifact path; resulting code runs with the SageMaker execution role's IAM permissions in versions 2.199.0 through 2.257.1 and 3.0.0 through 3.7.1.
Summary
What happened
Unsafe deserialization in Amazon SageMaker Python SDK allows remote authenticated users to execute code in inference containers. The Triton inference handler loads pickle-based model artifacts from S3 without verifying their integrity, so a replaced artifact executes automatically at the next container lifecycle event. Exploitation requires ModelBuilder with Triton and S3 write access to the model artifact path; resulting code runs with the SageMaker execution role's IAM permissions in versions 2.199.0 through 2.257.1 and 3.0.0 through 3.7.1.
The record
- CVE
- CVE-2026-8597
- Published
- May 14, 2026
- Updated
- May 14, 2026
- Vendor
- Amazon Web Services
- Product
- Amazon SageMaker Python SDK
- Classifications
- CWE-354, T1190
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- May 14, 2026CVE publishedPublication date reported by the CVE source.
- May 14, 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=2.199.0 <=2.257.1
- Affected versionversion=3.0.0 <=3.7.1
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