[ CVE-2026-105699 · Published 5 Oct 2026 ]
Langflow has Authenticated Cross-Project File Disclosure via Unscoped MCP Resource Handlers
[ Why it matters ]Priority signals
- Public proof-of-concept exploit exists (CISA SSVC)
[ Description ]Official description
Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.6.8 until 1.9.1, Langflow authenticated access to the project identifier in a project-scoped MCP connection but did not authorize the resource URI supplied to resources/read. read_resource forwarded the attacker-controlled URI to handle_read_resource, which parsed a flow_id and filename and called storage_service.get_file without verifying that the flow belonged to the authenticated user or current project. A user with access to any project-scoped MCP endpoint could therefore request another user's flow-backed file, while global handle_list_resources and handle_list_tools behavior could disclose flow and file identifiers that made targeting easier. The vulnerability disclosed uploaded documents, structured data, prompts, and other private flow artifacts across tenants but did not modify victim files or stored flows. This issue is fixed in version 1.9.1.
[ Fixes ]Fixes and patches
- langflow 1.9.1Fixed version · GitHub Advisories · pip package langflow: upgrade to 1.9.1 or later (affected >= 1.6.8, <= 1.9.0)
[ Packages ]Affected open-source packages
- langflow pipAffected >= 1.6.8, <= 1.9.0 · fixed in 1.9.1 · GHSA-4hmc-cfm3-w43c
[ References ]References
- github.com/langflow-ai/langflow/commit/b8fe970493fd5fb2e1fc71dfccc79f90b76058fa
- github.com/langflow-ai/langflow/commit/f0fd436fe9829192ee550e6cb46961a01dd37032
- github.com/langflow-ai/langflow/pull/12818
- github.com/langflow-ai/langflow/releases/tag/v1.9.1
- github.com/langflow-ai/langflow/security/advisories/GHSA-4hmc-cfm3-w43c