HighVulnerability

CVE-2026-8597: Amazon SageMaker Python SDK code execution via pickle model artifacts in S3

Source: NVD(opens in a new tab)
Identifier: CVE-2026-8597
Published: May 14, 2026
Record updated: October 9, 2026

Affected: sagemaker >= 2.199.0, <= 2.257.1, fixed in 2.257.2
sagemaker >= 3.0.0, <= 3.7.1, fixed in 3.8.0
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.6%

Summary

Missing integrity verification in the Triton inference handler in Amazon SageMaker Python SDK v2 before v2.257.2 and v3 before v3.8.0 lets a remote authenticated actor with S3 write access to the model artifact path replace model artifacts with a crafted pickle payload. The payload is deserialized without verification, allowing code execution in inference containers.

Mitigation

Upgrade to Amazon SageMaker Python SDK v2.257.2 or v3.8.0, and rebuild any Triton models previously created with ModelBuilder using the updated SDK.

Details

Scores and exploitation

CVSS score: 7.2(high)
Patch available: Yes
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H
Attack vector: network
Attack complexity: low
Privileges required: high
User interaction: none
EPSS: 0.6%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 14, 2026.
Disclosure date: May 14, 2026

Weaknesses and techniques

Weakness (CWE): CWE-354
AI threat technique (MITRE ATLAS): AML.T0010

Affected

Packages: sagemaker@>= 2.199.0, <= 2.257.1 (fixed: 2.257.2)
sagemaker@>= 3.0.0, <= 3.7.1 (fixed: 3.8.0)
Vendors: Amazon

Classification

Attack type: Supply chain
Attack sophistication: Moderate
AI component targeted: Inference
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-8597

First tracked: May 14, 2026 at 08:12 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

sagemakerPyPILLM dependency since 2024-07-10 · 3 tracked dependents

Topics

Inference infrastructure

Summary

Mitigation

Affected packages in the Exposure Registry

Topics

Related items