Vulnerability · CVE-2026-31252
CosyVoice thru commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e (2025-30-21) contains an insecure deserialization vulnerability (CWE-502) in its model loading component.
Published May 11, 2026 · catalog updated Jun 17, 2026 · CosyVoice thru commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e
Check if you run it
No confirmed exploitation is on record for CVE-2026-31252. EPSS is 0.30%. Act only if a listed version of CosyVoice thru commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e is installed.
Gaps on this record
- The stored product name is a package slug. The name on this page is taken from the title (CosyVoice thru commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e).
- No version range is stored. A customer cannot check an installed version against this record.
- No vendor fix or required action is stored. Compare the linked advisory before you change production.
- Severity
- Medium5.7
- Known exploitation
- Not in CISA/VulnCheck KEV
- EPSS
- 0.30%
- Remediation
- Not established
- Affected products
- See sources for product scope
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.
No affected version ranges are stored yet. Use the vendor advisory before you decide this record does not apply.
How to fix CVE-2026-31252
Recommended remediation
No required-action text, fix commit, or clear fixed-version range is stored yet.
Official advisories
What to do
Three questions, each answered from this record only. Confirm the vendor advisory before you patch.
Should you patch?
No confirmed exploitation is on record for CVE-2026-31252. EPSS is 0.30%. Act only if a listed version of CosyVoice thru commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e is installed.
Which versions are affected?
Affected version ranges are not on this record. Compare the installed version with the linked vendor advisory before you change production.
What should an analyst verify?
CWE-915: Improperly Controlled Modification of Dynamically-Determined Object Attributes; CWE-94: Code Injection. EPSS 0.30%. There is no CISA KEV listing. No Exploit-DB or Metasploit reference is linked. Use the source links for the original advisory.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
May 11, 2026 · NIST NVD
Detected
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
Jun 17, 2026 · NIST NVD
Updated
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
Sources
- CVE.orgVulnerability recordCVE-2026-31252
Official CVE identifier
cve.org - FIRST EPSSExploitation probabilityCVE-2026-31252
30-day exploitation probability 0.3%
first.org - NIST NVDVulnerability recordCVE-2026-31252
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 th
nvd.nist.gov
References
Freshness
Last verified in this catalog Oct 18, 2026. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.