Answer in brief
CVE-2026-104873 records a High severity (CVSS 7.6) vulnerability in LangGraph SDK custom auth silently ignores actions= on resource decorators. The current sources do not mark it as known exploited. The current feed maps langchain-ai/langgraph (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 7.6. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps langchain-ai/langgraph (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| langchain-ai/langgraphgeneric | >=0.1.45 <0.4.4 | 0.4.4 |
Published upstream
Oct 2, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Oct 2, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Oct 2, 2026
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.
Quoted source text, attributed separately from HOL analysis.