CVE-2026-31252
Published:May 11, 2026
Updated:May 16, 2026
CosyVoice thru commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e (2025-30-21) contains an insecure deserialization vulnerability (CWE-502) in its model loading component. The framework uses torch.load() to load model weight files (e.g., llm.pt, flow.pt, hift.pt) without enabling the security-restrictive weights_only=True parameter. This allows the deserialization of arbitrary Python objects via the pickle module. An attacker can exploit this by providing a malicious model directory containing specially crafted model files. When a victim starts the CosyVoice Web UI pointing to this directory, arbitrary code is executed on the victim's system during the model loading process.
Affected Packages
https://github.com/FunAudioLLM/CosyVoice.git (GITHUB):
Affected version(s) =v2.0 <55e3e370a0Fix Suggestion:
Update to version 55e3e370a0Related Resources (2)
Do you need more information?
Contact UsCVSS v4
Base Score:
2.4
Attack Vector
LOCAL
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
PASSIVE
Vulnerable System Confidentiality
LOW
Vulnerable System Integrity
LOW
Vulnerable System Availability
LOW
Subsequent System Confidentiality
LOW
Subsequent System Integrity
LOW
Subsequent System Availability
LOW
CVSS v3
Base Score:
5.7
Attack Vector
LOCAL
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
REQUIRED
Scope
CHANGED
Confidentiality
LOW
Integrity
LOW
Availability
LOW
Weakness Type (CWE)
EPSS
Base Score:
0.02