CVE-2026-8597: Amazon SageMaker Python SDK is missing integrity verification in its Triton inference handler
Summary Amazon SageMaker Python SDK is an open-source library for training and deploying machine learning models on Amazon SageMaker. An issue exists where, under certain circumstances, the Triton inference handler deserializes model artifacts without performing integrity verification, allowing specially crafted pickle payloads to execute arbitrary code.
Published May 21, 2026
Affected packages
sagemaker
- Ecosystem
- PyPI
- Affected
- >= 2.199.0, <= 2.257.1
- Fixed in
- 2.257.2
- Check
pip show sagemaker
sagemaker
- Ecosystem
- PyPI
- Affected
- >= 3.0.0, <= 3.7.1
- Fixed in
- 3.8.0
- Check
pip show sagemaker
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
Summary
Amazon SageMaker Python SDK is an open-source library for training and deploying machine learning models on Amazon SageMaker. An issue exists where, under certain circumstances, the Triton inference handler deserializes model artifacts without performing integrity verification, allowing specially crafted pickle payloads to execute arbitrary code.
Impact
When using ModelBuilder with the Triton inference server, the Triton handler did not perform integrity verification before deserializing model artifacts. A remote authenticated actor with S3 write access to the model artifact path could replace model files with a crafted payload that would execute automatically on the next container lifecycle event, achieving code execution with the SageMaker execution role's IAM permissions.
Impacted versions: >= v2.199.0 AND <= v2.257.1, >= v3.0.0 AND <= v3.7.1
Patches
This issue has been addressed in Amazon SageMaker Python SDK v2.257.2 and v3.8.0. The Triton inference handler now performs integrity verification before deserializing model artifacts. AWS recommend upgrading to the latest version and rebuilding any Triton models previously created with ModelBuilder using the updated SDK. Ensure any forked or derivative code is patched to incorporate the new fixes.
Workarounds
If upgrading is not immediately possible, users should restrict S3 write access to model artifact paths to only trusted principals and monitor for unintended modifications to files in model artifact S3 locations.
References
If there any questions or comments about this advisory, contact AWS Security via vulnerability reporting page or directly via email to [[email protected]](mailto:[email protected]). Please do not create a public GitHub issue.
References
- https://github.com/aws/sagemaker-python-sdk/security/advisories/GHSA-rq6v-x3j8-7qgf
- https://nvd.nist.gov/vuln/detail/CVE-2026-8597
- https://aws.amazon.com/security/security-bulletins/2026-031-aws
- https://github.com/aws/sagemaker-python-sdk/releases/tag/v2.257.2
- https://github.com/aws/sagemaker-python-sdk/releases/tag/v3.8.0
- https://github.com/advisories/GHSA-rq6v-x3j8-7qgf
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
More PyPI vulnerabilities
All PyPI entriesCVE-2026-8596
Cleartext storage of HMAC signing key in Amazon SageMaker Python SDK ModelBuilder/Serve path
high7.2May 21, 2026GHSA-5r2p-pjr8-7fh7
SageMaker Python SDK replaced eval() with safe parser in JumpStart search functionality
high8.4Mar 5, 2026CVE-2026-1777
SageMaker Python SDK has Exposed HMAC
high7.2Feb 2, 2026CVE-2026-1778
SageMaker Python SDK has Insecure TLS Configuration
high5.9Feb 2, 2026CVE-2025-0508
SageMaker Workflow component allows possibility of MD5 hash collisions
medium5.9Mar 20, 2025CVE-2024-34072
sagemaker-python-sdk vulnerable to Deserialization of Untrusted Data
high7.8May 3, 2024
