CVE-2025-67729 json
lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()
published 2025-12-26 10 mo ago modified 2026-10-07 32 d ago also EUVD-2025-205455 , GHSA-9pf3-7rrr-x5jh , PYSEC-2026-1578
- cvss
- 8.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.5%
- EPSS 0.5% chance of exploitation in 30 days, percentile 43%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 10 mo ago
Exploit prediction
0.51% chance of exploitation in the next 30 days, higher than 43% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | lmdeploy | <0.11.1 |
0.11.1 |
Affected products
- InternLM lmdeploy
Classification
- Weakness
-
- CWE-502 Deserialization of Untrusted Data
References
-
github.com
/InternLM/lmdeploy/commit/eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee
web, patch
-
github.com
/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh
exploit, web, vendor-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2025-67729
advisory
-
github.com
/InternLM/lmdeploy
package
-
pypi.org
/project/lmdeploy
package
-
github.com
/advisories/GHSA-9pf3-7rrr-x5jh
advisory
Sources
- CVE List CVE-2025-67729
- GitHub Advisory GHSA-9pf3-7rrr-x5jh
- NVD CVE-2025-67729
- OSV PYSEC-2026-1578
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.