LangGraph checkpoint loading has unsafe msgpack deserialization
CVE-2026-28277 · GHSA-g48c-2wqr-h844 · published 2026-03-05 · updated 2026-06-06
- Severity
- Medium
- CVSS score
- 6.8
- Chance of exploitation (EPSS)
- 5.5%
- Fixed in
- 1.0.10
- Exploitation No known exploitation
- Automatable No
- Technical impact Total
- CISA SSVC
Potential arbitrary code execution or other unsafe side effects during checkpoint deserialization. Escalation from “write access to checkpoint store” to “code execution in the application runtime,” which may expose runtime secrets or provide access to other systems the runtime can reach.
Upgrade langgraph to 1.0.10 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
LangGraph provides an allowlist-based hardening mechanism for msgpack checkpoint deserialization.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| langgraph | PyPI | <= 1.0.9 | 1.0.10 |
1 registered MCP server installs an affected version today, by the dependency versions a fresh install resolves.
- io.github.airas-org/airaslanggraph@1.0.3
- 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
- CriticalSGLang: Unauthenticated RCE via --enable-custom-logit-processorsglang
- CriticalSGLanG: Multimodal scheduler deserializes untrusted pickle data on 0.0.0.0 ROUTER socketsglang
- Criticaln8n: HTTP Request Node Pagination Prototype Pollution to RCEn8n, n8n, n8n
- Criticaln8n Has an XML Node Prototype Pollution Patch Bypassn8n, n8n, n8n
- MediumLangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requestslanggraph-sdk, langgraph
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.