lmdeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out
CVE-2026-46517 · GHSA-9xq9-36w5-q796 · published 2026-05-21 · updated 2026-08-31
- Severity
- High
- CVSS score
- 7.8
- Chance of exploitation (EPSS)
- 0.16%
- Fixed in
- 0.13.0
- Exploitation No known exploitation
- Automatable No
- Technical impact Total
- CISA SSVC
> ## 📋 Reframing (2026-05-02): implicit unsafe remote-code path, not "supply-chain" > > The accurate description of this vulnerability is: > "getmodelarch and related helpers hardcode trustremotecode=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.
Upgrade lmdeploy to 0.13.0 or later.
Replace every hardcoded trustremotecode=True with an explicit opt-in via CLI flag:
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| lmdeploy | PyPI | <= 0.12.3 | 0.13.0 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- CriticalLMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.pylmdeploy
- CriticalLMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploylmdeploy
- HighLMDeploy has an SSRF bypasslmdeploy
- HighLMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loadinglmdeploy
- HighLMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initializationlmdeploy
- HighLMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loadinglmdeploy
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.