langchain-ai langgraph langgraph-sdk get_tree/_fetch_state assistant_id/thread_id path traversal

Summaryinfo

A vulnerability, which was classified as problematic, was found in langchain-ai langgraph. Affected by this issue is the function get_tree/_fetch_state of the component langgraph-sdk. The manipulation of the argument assistant_id/thread_id results in path traversal. This vulnerability is known as CVE-2026-118667. It is possible to launch the attack remotely. No exploit is available.

Detailsinfo

A vulnerability classified as problematic has been found in langchain-ai langgraph (affected version not known). Affected is the function get_tree/_fetch_state of the component langgraph-sdk. The manipulation of the argument assistant_id/thread_id with an unknown input leads to a path traversal vulnerability. CWE is classifying the issue as CWE-22. The product uses external input to construct a pathname that is intended to identify a file or directory that is located underneath a restricted parent directory, but the product does not properly neutralize special elements within the pathname that can cause the pathname to resolve to a location that is outside of the restricted directory. This is going to have an impact on confidentiality. CVE summarizes:

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.

The advisory is shared for download at github.com. This vulnerability is traded as CVE-2026-118667 since 10/28/2026. The exploitability is told to be easy. It is possible to launch the attack remotely. There are known technical details, but no exploit is available. The current price for an exploit might be approx. USD $0-$5k (estimation calculated on 10/28/2026). The MITRE ATT&CK project declares the attack technique as T1006.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

Once again VulDB remains the best source for vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• langchain-ai

Name

• langgraph

Website

• Product: https://github.com/langchain-ai/langgraph/

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Once again VulDB remains the best source for vulnerability data.

Discussion