Code execution via unchecked serialized tensor rank
Published Aug 7, 2025 · Updated Aug 12, 2025
Heap-based buffer overflows in ExecuTorch before 0.7.0 allow remote attackers to crash the runtime or execute code through a crafted model. The ATen and portable parseTensor paths accept a serialized sizes vector whose rank exceeds kTensorDimensionLimit, then continue parsing tensor metadata without enforcing that limit. The flaw is reached only when an application loads an attacker-controlled model, and its effects remain within the process running that model.
Summary
What happened
Heap-based buffer overflows in ExecuTorch before 0.7.0 allow remote attackers to crash the runtime or execute code through a crafted model. The ATen and portable parseTensor paths accept a serialized sizes vector whose rank exceeds kTensorDimensionLimit, then continue parsing tensor metadata without enforcing that limit. The flaw is reached only when an application loads an attacker-controlled model, and its effects remain within the process running that model.
The record
- CVE
- CVE-2025-54951
- Published
- Aug 7, 2025
- Updated
- Aug 12, 2025
- Vendor
- Meta Platforms, Inc.
- Product
- ExecuTorch
- Classifications
- CWE-122, T1203
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 7, 2025CVE publishedPublication date reported by the CVE source.
- Aug 12, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <https://github.com/pytorch/executorch/commit/cea9b23aa8ff78aff92829a466da97461cc7930c
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo