0.0
NA
CVE-2026-31252
CosyVoice Insecure Deserialization Vulnerability
Description

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.

INFO

Published Date :

May 11, 2026, 5:16 p.m.

Last Modified :

May 11, 2026, 5:16 p.m.

Remotely Exploit :

No
Affected Products

The following products are affected by CVE-2026-31252 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

No affected product recoded yet

Solution
Enable security features for model loading to prevent arbitrary code execution.
  • Update CosyVoice to a version that enables weights_only=True.
  • Ensure model files are loaded securely.
  • Use only trusted model sources.
References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2026-31252.

URL Resource
https://github.com/FunAudioLLM/CosyVoice
https://www.notion.so/CVE-2026-31252-35d1e139318881ef8acfcd877a432569
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-31252 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-31252 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-31252 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-31252 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • New CVE Received by [email protected]

    May. 11, 2026

    Action Type Old Value New Value
    Added Description 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.
    Added Reference https://github.com/FunAudioLLM/CosyVoice
    Added Reference https://www.notion.so/CVE-2026-31252-35d1e139318881ef8acfcd877a432569
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.