Skip to main content

Deserialization of Untrusted Data

CVE-2026-31239

High
9.8/10

Summary

The mamba language model framework through 2.2.6 is vulnerable to Insecure Deserialization (CWE-502) when loading pre-trained models from HuggingFace Hub. The MambaLMHeadModel.from_pretrained() method uses torch.load() to load the pytorch_model.bin weight file 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 publishing a malicious model repository on HuggingFace Hub. When a victim loads a model from this repository, arbitrary code is executed on the victim's system in the context of the mamba process.

  • LOW
  • NETWORK
  • HIGH
  • UNCHANGED
  • NONE
  • NONE
  • HIGH
  • HIGH

CWE-502 - Deserialization of Untrusted Data

Deserialization of untrusted data vulnerabilities enable an attacker to replace or manipulate a serialized object, replacing it with malicious data. When the object is deserialized at the victim's end the malicious data is able to compromise the victim’s system. The exploit can be devastating, its impact may range from privilege escalation, broken access control, or denial of service attacks to allowing unauthorized access to the application's internal code and logic which can compromise the entire system.

References

Advisory Timeline

  • Published