Skip to main content
VulnerabilityPublished

CVE-2026-118667: langchain-ai langgraph · Path Traversal

Affects langchain-ai langgraphSource CVE Database V5

0

Not known to be exploited · CVSS 4.3 Medium : upgrade to 1.2.14 when convenient.

Data as of 28 Oct 2026, 21:14 UTC

CVSS 3.1 base score
4.3Medium
How severe the flaw is on the 0–10 CVSS scale.
Patch
Available – fixed in 1.2.14, 0.4.6
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 28 Oct 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponised: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

What to do

Upgrade langgraph to 1.2.14; langgraph-sdk to 0.4.6.

Affected software

ProductAffectedFixed in
langchain-ailanggraphAffected
  • >=1.2.3 <1.2.14
Fixed in
  • 1.2.14
langchain-ailanggraph-sdkAffected
  • >=0.4.0 <0.4.6
Fixed in
  • 0.4.6

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Upgrade langgraph-sdk to version 0.4.6 or later and langgraph to version 1.2.14 or later to apply the official fixes that properly encode path parameters and prevent path traversal. No other mitigation is indicated or required.

Description

A path traversal vulnerability (CWE-22) exists in langchain-ai's langgraph Python SDK and langgraph versions prior to 0.4.6 and 1.2.14 respectively. The issue arises when certain helper functions interpolate user-controlled assistant_id and thread_id values into authenticated GET request paths without proper encoding, allowing relative path segments to access unintended server paths. This vulnerability is fixed in langgraph-sdk 0.4.6 and langgraph 1.2.14.

References

Community reviews

Loading reviews…