High severity · published Oct 2, 2026
CVE-2026-104873
LangGraph SDK custom auth silently ignores actions= on resource decorators
7.6
CVSS
0.3%
EPSS
No
On KEV
Description
LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From 0.1.45 until 0.4.4, the langgraph-sdk resource-scoped authorization decorators @auth.on.threads, @auth.on.assistants, and @auth.on.crons ignore the actions argument and register the selected handler for every action on the resource. Because that wildcard resource handler is selected before broader fallback handlers, an authenticated user may bypass fallback action, ownership, or permission checks and read, update, or delete another user's resource. Only Python deployments using actions on the affected decorators are vulnerable, and a deployment remains protected when the selected handler independently enforces all required checks for every action it receives. This issue is fixed in version 0.4.4.
Exploitation
Is it being used?
Exploit prediction (EPSS)0.3% · higher than 17% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LA
langgraph · langchain-ai
>= 0.1.45, < 0.4.4 · source: vendor
Affected product
LA
langgraph
langchain-ai
More from langgraph
7.8
CVE-2025-67644
LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method
7.4
CVE-2025-64439
LangGraph Checkpoint affected by RCE in "json" mode of JsonPlusSerializer
7.3
CVE-2025-64104
LangGraph SQLite Checkpoint Filter Key SQL Injection POC for SqliteStore
7.2
CVE-2026-28277
LangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loading
6.8
CVE-2026-48775
LangGraph Checkpoint: Unsafe JSON deserialization in checkpoint loading