Findings

CVE-2026-27905

BentoML is a Python library for building online serving systems optimized for AI apps and model inference.

Published Mar 3, 2026 · updated Oct 7, 2026 · bentoml bentoml

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.36, the safe_extract_tarfile() function validates that each tar member's path is within the destination directory, but for symlink members it only validates the symlink's own path, not the symlink's target. An attacker can create a malicious bento/model tar file containing a symlink pointing outside the extraction directory, followed by a regular file that writes through the symlink, achieving arbitrary file write on the host filesystem. This vulnerability is fixed in 1.4.36.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. Mar 3, 2026 · NIST NVD

    Detected

    BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.36, the safe_extract_tarfile() function validates that each tar member's path is within the destination directory, but for symlink members it only validates the symlink's own path, not the symlink's target. An attacker can create a malicious bento/model tar file containing a syml

  2. Oct 7, 2026 · NIST NVD

    Updated

    BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.36, the safe_extract_tarfile() function validates that each tar member's path is within the destination directory, but for symlink members it only validates the symlink's own path, not the symlink's target. An attacker can create a malicious bento/model tar file containing a syml

Affected

  • cpe bentoml/bentomlversion unspecified

Sources

  • CVE.orgVulnerability recordCVE-2026-27905

    Official CVE identifier

    cve.org
  • NIST NVDVulnerability recordCVE-2026-27905

    BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.36, the safe_extract_tarfile() function validates that each tar member's path is within the destination directory, but for symlink members it only validates the

    nvd.nist.gov

References