CVE-2025-27520
Published: 04 April 2025
Summary
CVE-2025-27520 is a critical-severity Deserialization of Untrusted Data (CWE-502) vulnerability in Bentoml Bentoml. Its CVSS base score is 9.8 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 1.1% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as NLP and Transformers; in the Supply Chain and Deployment risk domain.
Deeper analysis
BentoML is a Python library for building online serving systems optimized for AI applications and model inference. CVE-2025-27520 is a remote code execution vulnerability caused by insecure deserialization in version 1.4.2, residing in an unsafe code segment within serde.py. The flaw carries a CVSS score of 9.8 and is categorized under CWE-502.
Any unauthenticated remote attacker can exploit the issue over the network to execute arbitrary code on the server with no user interaction required, achieving full confidentiality, integrity, and availability impact.
The vulnerability is fixed in release 1.4.3, as noted in the project's GitHub security advisory GHSA-33xw-247w-6hmc and the associated commit that addresses the deserialization logic.
BentoML's focus on AI model serving makes the flaw particularly relevant to machine-learning infrastructure. The associated EPSS score reached a peak of 0.8735 with a current value of 0.7576, indicating notable post-disclosure exploitation interest.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-9752
Vulnerability details
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. A Remote Code Execution (RCE) vulnerability caused by insecure deserialization has been identified in the latest version (v1.4.2) of BentoML. It allows any…
more
unauthenticated user to execute arbitrary code on the server. It exists an unsafe code segment in serde.py. This vulnerability is fixed in 1.4.3.
- CWE(s)
AI Security AnalysisAI
- AI Category
- NLP and Transformers
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, bentoml
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The insecure deserialization vulnerability (CWE-502) in BentoML's HTTP API endpoints (e.g., /summarize) enables unauthenticated remote code execution via malicious pickle payloads, directly mapping to exploitation of public-facing applications.
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Penetration testing supplies malicious serialized objects, detecting unsafe deserialization and supporting corrective actions.
Evaluation of untrusted data handling (deserialization testing) reveals unsafe processing, which the required remediation process addresses.
Untrusted serialized data can be deserialized and observed inside the chamber, blocking gadget-chain exploitation outside the sandbox.
Validates or rejects untrusted serialized data before deserialization occurs.
Identifies and blocks malicious code introduced through deserialization of untrusted data at system boundaries.
Integrity verification of serialized information can detect tampering before deserialization occurs.
Provenance of associated data allows detection of untrusted sources before deserialization or processing occurs.