CVE-2026-31252: FunAudioLLM CosyVoice insecure deserialization in model loading

CVE-2026-31252 · Severity: medium · CVSS 5.7 · Published 2026-05-11

CosyVoice, a multi-lingual voice generation framework, is vulnerable to a security flaw in how it loads AI model files. If a user is tricked into loading a malicious model file from an untrusted source, an attacker can execute unauthorized commands on the user's computer. This could lead to a full system compromise, data theft, or the installation of malware.

Technologies: FunAudioLLM CosyVoice. Vendors: FunAudioLLM.

Quick answers

Is CVE-2026-31252 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-31252 being exploited in the wild.
How severe is CVE-2026-31252?
Medium severity, with a CVSS score of 5.7, published 11 May 2026.
Which products and versions are affected?
FunAudioLLM CosyVoice up to commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e.
Is there a fix for CVE-2026-31252?
No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.
How is CVE-2026-31252 attacked?
It is attacked with local access, in a software library.
Am I affected by CVE-2026-31252?
Check whether you run FunAudioLLM CosyVoice at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

Technical details

CosyVoice (up to commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e) is vulnerable to insecure deserialization (CWE-502) within its model loading component. The application utilizes the `torch.load()` function to process model weight files (such as llm.pt, flow.pt, and hift.pt) without setting the `weights_only=True` parameter. Because `torch.load` uses the Python pickle module by default, it can be coerced into deserializing arbitrary Python objects. An attacker can exploit this by providing a malicious model directory; when a victim points the CosyVoice Web UI to this directory, the framework executes arbitrary code embedded in the model files.

Affected products

  • FunAudioLLM CosyVoice up to commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e

Timeline

  • 2026-05-11: advisory: CVE-2026-31252 published by NVD

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.