HighVulnerability

CVE-2026-31252: CosyVoice insecure deserialization in model loading via torch.load

Source: NVD(opens in a new tab)
Identifier: CVE-2026-31252
Published: May 11, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.1%

Summary

CosyVoice, through commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e (2025-30-21), has an insecure deserialization flaw (CWE-502) in its model loading component. The framework calls torch.load() on model weight files such as llm.pt, flow.pt and hift.pt without weights_only=True, so arbitrary Python objects can be deserialized through the pickle module. When a victim starts the CosyVoice Web UI pointing at a malicious model directory, arbitrary code runs on their system during model loading.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

EPSS: 0.1%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 6, 2026.
Disclosure date: May 11, 2026

Weaknesses and techniques

AI threat technique (MITRE ATLAS): AML.T0010

Classification

Attack type: Supply chain
Attack sophistication: Moderate
AI component targeted: Inference
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-31252

First tracked: May 11, 2026 at 02:10 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Topics

Model and package supply chain

Summary

Mitigation

Topics

Related items