CVE-2025-32375: BentoML insecure deserialization in runner server via crafted POST request

Summary

CVE-2025-32375 affects BentoML, a Python library for building online serving systems for AI apps and model inference, prior to 1.4.8. Insecure deserialization (CWE-502) in BentoML's runner server lets an attacker set specific headers and parameters in a POST request to execute arbitrary code on the server, gaining initial access and information disclosure.

Mitigation

Fixed in 1.4.8.

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.

• bentomlPyPINo LLM dependency detected · 1 tracked dependent

Related items

• MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
• MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
• HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
• InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
• MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online