CVE Catalog

CVE-2026-31251

High
Published: Translated: NVD NIST

Summary

CosyVoice contains an insecure deserialization vulnerability in its gRPC server component. The issue arises because the server loads the speech synthesis model from a user-specified directory without enabling the weights_only=True security parameter, allowing the deserialization of arbitrary Python objects.

Risk Assessment

An attacker can exploit this vulnerability by providing malicious model files, leading to arbitrary code execution on the victim's system during server initialization.

Recommendation

It is recommended to enable the weights_only=True parameter when loading models and to verify the source of model files before use.

Related vulnerabilities

Original NVD description (English source)

CosyVoice thru commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e (2025-30-21) contains an insecure deserialization vulnerability (CWE-502) in its gRPC server component. When the server starts, it loads the speech synthesis model from a user-specified directory using torch.load() without enabling the weights_only=True security parameter. This allows the deserialization of arbitrary Python objects via the pickle module. An attacker can exploit this by providing malicious model files within a directory. When a victim starts the gRPC server pointing to this directory, arbitrary code is executed on the victim's system during server initialization.

Vulnerability data from NVD (NIST) · CISA KEV · EPSS