MediumVulnerability

CVE-2023-48299: TorchServe archive extraction path traversal via model management API

Source: NVD(opens in a new tab)
Identifier: CVE-2023-48299
Published: November 21, 2023
Record updated: October 9, 2026

Affected: torchserve >= 0.1.0, < 0.9.0
Fixed in: 0.9.0
released October 12, 2023, 41 days before disclosure
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.7%

Summary

TorchServe versions from 0.1.0 up to but not including 0.9.0 are affected by CVE-2023-48299. Through the model/workflow management API, an attacker can upload archives that extract files to any location the process can write to. This could let third parties hide harmful code in public models and compromise machines running TorchServe.

Mitigation

The ZipSlip issue has been fixed by validating the paths of files in a zip archive before extraction. TorchServe release 0.9.0 includes the fix.

Details

Scores and exploitation

CVSS score: 5.3(medium)
Patch available: Yes
EPSS: 0.7%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-22
Attack pattern (CAPEC): CAPEC-126
AI threat technique (MITRE ATLAS): AML.T0010

Affected

Packages: torchserve@>= 0.1.0, < 0.9.0 (fixed: 0.9.0)

Classification

Attack type: Supply chain
Attack sophistication: Moderate
AI component targeted: Inference
Impact: Integrity,
Confidentiality
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-2023-48299

First tracked: February 15, 2026 at 08:37 PM ET, from NVD/CVE Database

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

Classifier confidence: 95% (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.

torchservePyPINo LLM dependency detected

Summary

Mitigation

Affected packages in the Exposure Registry

Related items