# CVE-2026-76850: LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector

> Remote attackers can execute arbitrary code in LMDeploy engines by sending malicious pickle data to unauthenticated peer connectors when disaggregated serving is enabled.

- **Severity:** Critical 9.3 (`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`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 19 Aug 2026
- **Updated:** 24 Sep 2026
- **Also known as:** GHSA-q66m-3fcg-jjh7

## What is CVE-2026-76850?

CVE-2026-76850 is a critical unsafe deserialization vulnerability in InternLM lmdeploy, published on 19 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

### Official description

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.loads(), and the isinstance check against DistServeCacheFreeRequest runs only after deserialization has already completed. The peer that supplies those bytes is caller-controlled: p2p_connect passes remote_engine_endpoint_info.zmq_address from the request body to connect() on the ZMQ PULL socket, and the POST /distserve/p2p_initialize and /distserve/p2p_connect endpoints in lmdeploy/serve/openai/api_server.py apply no authentication unless the server is started with api_keys, which defaults to None. A remote attacker can direct an engine to pull from a ZMQ endpoint under their control and execute arbitrary code in the engine process. Deployments that do not enable disaggregated serving are not affected, because the receive loop is only started once the migration backend accepts the connection.

Weakness: CWE-502 (Deserialization of Untrusted Data)

## Which versions are affected by CVE-2026-76850?


## How do I fix CVE-2026-76850?

No fix has been published for CVE-2026-76850 yet. Limit exposure of the affected software until one is available.

## Is CVE-2026-76850 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-76850 exists.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-76850 and fix it if it is affected.

What it is: CVE-2026-76850 is a critical unsafe deserialization vulnerability in InternLM lmdeploy, published on 19 Aug 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Exploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-76850 exists.

Affected product: InternLM lmdeploy. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-76850/ (Markdown: https://insights.sbomify.com/CVE-2026-76850/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-76850
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-76850
- OSV: https://osv.dev/vulnerability/CVE-2026-76850

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-76850/
Summaries are generated and may contain mistakes; the official description above is the record.