CosyVoice through commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e contains an insecure deserialization vulnerability (CWE-502) in its make_parquet_list.py script. The script loads PyTorch .pt files (containing utterance embeddings, speaker embeddings, speech tokens) using torch.load() without enabling the weights_only=True security parameter. This omission allows deserialization of arbitrary Python objects via the pickle module. An attacker can craft malicious .pt files that, when processed by the tool, result in arbitrary code execution on the victim's system.

Successful exploitation allows an attacker to execute arbitrary code on the victim's system by providing malicious PyTorch .pt files to the data processing tool. This can lead to full compromise of the affected system where the tool is run. There are no reports of exploitation in the wild. The impact is local to systems running the vulnerable script.

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, users should avoid processing untrusted or unauthenticated PyTorch .pt files with the make_parquet_list.py tool. Consider manually modifying the script to use torch.load() with the weights_only=True parameter to mitigate insecure deserialization risks.