Sign in Sign up
JA · EN · FR
SecPulse
Categories
CVE-2026-46517 high CVSS 7.8

Code Injection in lmdeploy (CVE-2026-46517)

Summary

Code injection in lmdeploy (CVE-2026-46517). Successful exploitation can lead to full system takeover. Exploitable via get_model_arch. Mitigation: upgrade to 0.13.0 or later.

Original description

The description as published by the source.

📋 Reframing (2026-05-02): implicit unsafe remote-code path, not "supply-chain"

The accurate description of this vulnerability is:
"get_model_arch and related helpers hardcode trust_remote_code=True
with no opt-out, creating an implicit unsafe remote-code load path
on every model fetch."

What this report does NOT claim:

  • It is NOT a network-attack RCE — the user supplies the model
    reference; LMDeploy honors it.
  • It is NOT a "supply chain" CVE in the classical sense (where a
    benign upstream is compromised) — the user explicitly types the
    repo name.

What this report DOES claim:

  • Other inference frameworks (vLLM, TGI, Hugging Face transformers
    itself) all expose --trust-remote-code as opt-in so that
    users who consciously load known-safe repos can opt in, while
    users following a tutorial cannot accidentally execute attacker
    Python by typing a wrong repo name.
  • LMDeploy's hardcoded True is an implicit trust-boundary
    override that violates HF Transformers' default-secure stance
    (trust_remote_code=False since transformers ≥ 4.30).
  • The fix is a one-line CLI flag (--trust-remote-code) defaulting
    False, threaded through the three sites, matching the rest of
    the ecosystem.

Severity should be assessed as hardening / safe-by-default,
not as full unauthenticated RCE. CVSS revised to 5.5 Medium
(AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H × user-must-load qualifier).

Runtim…

Source: GitHub Security Advisories (Global) NVD GitHub Advisory

Auto-generated summary

Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.

A vulnerability tracked as CVE-2026-46517 has been found in lmdeploy.
Attackers can target a specific entry point like get_model_arch over the network to misuse the product.
Successful exploitation can lead to full system takeover. CVSS score: 7.8/10.
What to do: upgrade lmdeploy to 0.13.0 or later.
If unsure, ask your IT team or search "lmdeploy CVE-2026-46517" on the vendor's site.

CVE-2026-46517 (lmdeploy) — CWE-94 / CVSS v3 7.8
Attack vector: local / unauthenticated
Attack surface: get_model_arch / from_pretrained / True / vllm
Patched: 0.13.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.

❓ What is the problem

Arbitrary code execution (CWE-94) exists in lmdeploy. Attackers reach the vulnerable code path via get_model_arch without authentication.

📍 Affected scope

Check the vendor advisory for the affected versions of lmdeploy. Attack surface: get_model_arch / from_pretrained / True / vllm.

🔥 Severity

Severity: High (CVSS 7.8/10). Successful exploitation can lead to full system takeover.

🔧 How to fix

Update to 0.13.0.

🛡️ Workaround

Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.

🔍 Detection

Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'lmdeploy' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.

Response actions

Concrete steps and command examples for SOC/SRE teams to execute in order

  1. 1
    Identify exposure identify 
    grep -r 'lmdeploy' . | grep -v node_modules

    リポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で lmdeploy を grep し、稼働しているサービス・バージョンを把握する。

  2. 2
    Apply patch patch 
    Upgrade lmdeploy to 0.13.0

    ステージング環境で 0.13.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。

  3. 3
    Post-deployment verification verify 
    Confirm patched version is live in production

    パッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。

Affected packages

pip lmdeploy
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.13.0"}]}]
PyPI lmdeploy
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.12.3"}]}]

References

We use cookies for analytics and ad measurement. This setting applies to all Game co., Ltd. sites. Details