Skip to main content
VulnerabilityPublished Updated

CVE-2026-104873: langchain-ai langgraph · Incorrect Authorization

Affects langchain-ai langgraphSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 7.6 High : upgrade to 0.4.4 soon.

Data as of 16 Nov 2026, 20:25 UTC

CVSS 4.0 base score
7.6High
How severe the flaw is on the 0–10 CVSS scale.
EPSS
0.2% chance of exploitation in 30 days – higher than 16% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch
Available – fixed in 0.4.4
CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 2 Oct 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: 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 16 Nov 2026.

What to do

Upgrade langgraph and langgraph-sdk to 0.4.4.

Affected software

ProductAffectedFixed in
langchain-ailanggraphAffected
  • >=0.1.45 <0.4.4
Fixed in
  • 0.4.4
PyPIlanggraph-sdkpkg:pypi/langgraph-sdkOther threatsAffected
  • >=0.1.45 <0.4.4
Fixed in
  • 0.4.4

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 0.4.4 or later, where this authorization issue is fixed. Deployments that do not use the affected decorators or that have handlers enforcing all required checks are not vulnerable. No other mitigation is indicated.

Description

CVE-2026-104873 is an incorrect authorization vulnerability in the langgraph Python SDK used by langchain-ai. Versions from 0.1.45 up to but not including 0.4.4 have resource-scoped authorization decorators that ignore the actions argument, causing a wildcard handler to be selected for all actions. This allows authenticated users to bypass permission checks and access or modify other users' resources. The issue is fixed in version 0.4.4.

References

Community reviews

Loading reviews…