Vulnerability Description
LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weights_only=True parameter when loading model checkpoint files. This allows an attacker to execute arbitrary code on the victim's machine when they load a malicious .bin or .pt model file. This issue has been patched in version 0.11.1.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Internlm | Lmdeploy | < 0.11.1 |
Related Weaknesses (CWE)
References
- https://github.com/InternLM/lmdeploy/commit/eb04b4281c5784a5cff5ea639c8f96b33b3aPatch
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jhVendor Advisory
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jhVendor Advisory
FAQ
What is CVE-2025-67729?
CVE-2025-67729 is a vulnerability with a CVSS score of 8.8 (HIGH). LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weigh...
How severe is CVE-2025-67729?
CVE-2025-67729 has been rated HIGH with a CVSS base score of 8.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2025-67729?
Check the references section above for vendor advisories and patch information. Affected products include: Internlm Lmdeploy.