Security Digest · Vulnerability record
CVE-2025-32375: BentoML's runner server Vulnerable to Remote Code Execution (RCE) via Insecure Deserialization
BentoML is a Python library for building online serving systems optimized for AI apps and model inference.
CVSS 9.8 Critical EPSS 52.4% · p99
Should you act?
High exploit likelihood
EPSS ranks it in the top 5% of all CVEs for likely exploitation in the next 30 days. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 52.4%, percentile 99: FIRST’s model estimates a 52.4% chance of exploitation activity in the next 30 days, higher than 99% of all scored CVEs (very high). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
bentoml(PyPI) >= 1.0.0a1, < 1.4.8, fixed in 1.4.8. Check your lockfile, including transitive dependencies.
What it is
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.8, there was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8.
From the GitHub advisory
Summary There was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server.
PoC - First, create a file named model.py to create a simple model and save it
- Then run the following command to save this model
- Next, create bentofile.yaml to build this model
- Then, create service.py to host this model
Weakness type: CWE-502.
Product: bentoml (PyPI) · Assigned by: GitHub_M · Published: 2025-04-09
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | bentoml | >= 1.0.0a1, < 1.4.8 | 1.4.8 |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| bentoml | BentoML | >= 1.0, < 1.4.8 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_M | 3.1 | 9.8 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: none
- Scope: unchanged
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 52.41% probability of exploitation activity in the next 30 days; percentile 99.
Timeline
- — CVE record last updated
- — CVE record published by GitHub_M
- — GitHub-reviewed advisory GHSA-7v4r-c989-xh26 published (critical)
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-7v4r-c989-xh26 github.com
- CVE.org record CVE-2025-32375 cve.org
- NVD entry CVE-2025-32375 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com
- github.com github.com