Code execution via unsafe PyTorch model loading
Published May 11, 2026 · Updated May 11, 2026
Insecure deserialization in CosyVoice model loading allows local users to execute code through malicious model files. The loader passes llm.pt, flow.pt, and hift.pt files to torch.load without weights_only=True, permitting pickle to construct arbitrary Python objects. Execution occurs only when a victim starts the Web UI with the attacker-supplied model directory, and the payload runs with the victim process's privileges.
Summary
What happened
Insecure deserialization in CosyVoice model loading allows local users to execute code through malicious model files. The loader passes llm.pt, flow.pt, and hift.pt files to torch.load without weights_only=True, permitting pickle to construct arbitrary Python objects. Execution occurs only when a victim starts the Web UI with the attacker-supplied model directory, and the payload runs with the victim process's privileges.
The record
- CVE
- CVE-2026-31252
- Published
- May 11, 2026
- Updated
- May 11, 2026
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-915, CWE-94, CWE-502, T1204.002
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- May 11, 2026CVE publishedPublication date reported by the CVE source.
- May 11, 2026Record 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?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
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.
Weakness, pattern, technique
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