CVE-2025-32375 in the critical feed json
Insecure Deserialization leads to RCE in BentoML's runner server
published last yr. modified 4mo ago also GHSA-7v4r-c989-xh26 , PYSEC-2025-32 , EUVD-2025-10547
- cvss
- 9.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 52.4%
- EPSS 52.4% chance of exploitation in 30 days, percentile 98%
- public exploits
- 1
- Metasploit
Summary
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.
Patch / fix
- pypi bentoml 1.4.8
- bentoml bentoml 1.4.8
Is CVE-2025-32375 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerTimeline
- First public exploit (Metasploit exploit/linux/http/bentoml_runner_server_rce_cve_2025_32375)
- Published
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- last yr.
Exploit prediction
52.42% chance of exploitation in the next 30 days, higher than 98% of all scored CVEs (FIRST EPSS, 2026-11-09).
Exploits and checks
- Metasploit exploit/linux/http/bentoml_runner_server_rce_cve_2025_32375 BentoML's runner server RCE metasploit exploit, excellent rank, 2025-04-09
- github.com https://github.com/bentoml/BentoML/security/advisories/GHSA-7v4r-c989-xh26 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| NVD | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 9.8 | 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 |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | bentoml | >=1.0.0a1, <1.4.8 >=1.0.0, <1.4.8 |
1.4.8 |
Affected products
- bentoml BentoML
Classification
- Weakness
-
- CWE-502 Deserialization of Untrusted Data
References
-
github.com
/bentoml/BentoML/security/advisories/GHSA-7v4r-c989-xh26
exploit, web, vendor-advisory, advisory, evidence
-
nvd.nist.gov
/vuln/detail/CVE-2025-32375
advisory
-
github.com
/bentoml/BentoML
package
-
github.com
/pypa/advisory-database/tree/main/vulns/bentoml/PYSEC-2025-32.yaml
web
-
github.com
/advisories/GHSA-7v4r-c989-xh26
advisory
Sources
- CVE List CVE-2025-32375
- GitHub Advisory GHSA-7v4r-c989-xh26
- NVD CVE-2025-32375
- OSV PYSEC-2025-32
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.