CVE-2026-119706
LMDeploy 0.9.0 through 0.18.0 Unauthenticated RCE via /update_weights Pickle Deserialization
InternLM LMDeploy 0.9.0 through 0.18.0 contains an unauthenticated remote code execution vulnerability that allows remote attackers to run OS commands by sending pickled data to the /update_weights endpoint. Attackers can submit a base64-encoded crafted pickle in serialized_named_tensors, which ForkingPickler.loads deserializes without validation, executing commands as the api_server process.
Fixes and workarounds
Fix
The reporting source identifies this reference as a patch. Check the advisory for affected versions and supported release branches.
Source: CNA: VulnCheckAffected products and versions
| Product | Versions | Authority |
|---|---|---|
| lmdeploy InternLM lmdeploy
pypi |
≥ 0.9.0; ≤ 0.18.0 (affected, semver)
Other versions: unaffected |
CNA: VulnCheck |
Version ranges are source assertions. Check the vendor advisory and your installed configuration before determining exposure.
CVSS assessments
| Version / score | Vector | Authority |
|---|---|---|
| 4.0 / 9.3 critical |
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N | CNA: VulnCheck |
| 3.1 / 9.8 critical |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | CNA: VulnCheck |
Exploit evidence
- https://github.com/InternLM/lmdeploy/issues/4698
exploit · ADP: CISA-ADP
References
- https://github.com/InternLM/lmdeploy/issues/4698CNA: VulnCheck · issue-tracking
- https://github.com/InternLM/lmdeployCNA: VulnCheck · product
- https://github.com/InternLM/lmdeploy/blob/v0.18.0/lmdeploy/serve/openai/endpoints/management.py#L55-L60CNA: VulnCheck · technical-description
- https://github.com/InternLM/lmdeploy/blob/v0.18.0/lmdeploy/turbomind/turbomind.py#L345CNA: VulnCheck · technical-description
- https://github.com/InternLM/lmdeploy/pull/4964CNA: VulnCheck · patch, issue-tracking
- https://www.vulncheck.com/advisories/lmdeploy-0.9.0-through-0.18.0-unauthenticated-rce-via-update-weights-pickle-deserializationCNA: VulnCheck · third-party-advisory
- https://github.com/InternLM/lmdeploy/issues/4698ADP: CISA-ADP · exploit
For agents and automation
Read public disclosures for free as Markdown or JSON. Compatible browsers also expose native WebMCP tools to search disclosures, read this page, and discover API access.
Use the ontology-linked Cyber API with x402 pay per request, or a Y2 Pro or Elite API key with the intel:cyber scope.
Endpoints and access details
https://api.y2.dev/api/v2/cyber/cveshttps://api.y2.dev/api/v2/cyber/cves/{cveId}
A workspace owner or admin can create a Pro or Elite API key. Send Authorization: Bearer <Y2_API_KEY> from your trusted agent runtime.
For x402, omit Authorization and read the HTTP 402 payment challenge before signing a retry. Public browser tools do not make payments.