CVE-2025-59953 json
LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy
published 2026-09-16 53 d ago modified 2026-10-14 25 d ago also EUVD-2025-210921 , GHSA-5h8j-6crg-7rmw , PYSEC-2026-4079
- cvss
- 9.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.9%
- EPSS 0.9% chance of exploitation in 30 days, percentile 59%
- public exploits
- 0
- none known
Summary
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server (AsyncRPCServer in zmq_rpc.py) for supporting the RPC communications. In its core functionality call_and_response(), I found it will directly use the pickles.loads() to deserialize the received messages without any sanitization, hence resulting in a remote code execution vulnerability by this RPC server. Version 0.10.2 contains a patch.
Patch / fix
- pypi lmdeploy 0.10.2
- internlm lmdeploy 0.10.2
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 51 d ago
Exploit prediction
0.88% chance of exploitation in the next 30 days, higher than 59% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | lmdeploy | >=0.9.1, <0.10.2 |
0.10.2 |
Affected products
- InternLM lmdeploy
Classification
- Weakness
-
- CWE-502 Deserialization of Untrusted Data
References
-
github.com
/InternLM/lmdeploy/commit/d86046a0e6b02ecaaf7cdb74346d0477130221c2
web
-
github.com
/InternLM/lmdeploy/security/advisories/GHSA-5h8j-6crg-7rmw
exploit, web
-
github.com
/InternLM/lmdeploy/releases/tag/v0.10.2
web
-
nvd.nist.gov
/vuln/detail/CVE-2025-59953
advisory
-
github.com
/InternLM/lmdeploy
package
-
pypi.org
/project/lmdeploy
package
-
github.com
/advisories/GHSA-5h8j-6crg-7rmw
advisory
Sources
- CVE List CVE-2025-59953
- GitHub Advisory GHSA-5h8j-6crg-7rmw
- NVD CVE-2025-59953
- OSV PYSEC-2026-4079
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.