2026-10-15 · 2026-Q4
Langflow MCP stdio RCE Exploited in the Wild: 1,706 Attempts Steal Secret Keys and Superuser Passwords (CVE-2026-105740)
Who wrote the file that runs on open?
- Fixable
- Vendor patch
- Vendor response
- Patched
- In the wild
- Yes
- Actor
- Attacker
Target
Langflow versions before 1.9.0
Impact
Any authenticated user, including a non-admin, can POST an MCP server with stdio transport to `/api/v2/mcp/servers/{name}` whose command runs unvalidated when the server list is fetched; the `env` field also accepts `LD_PRELOAD` and `PATH` overrides, and the config persists and re-runs on every load. Previdian honeypots logged 1,706 exploitation attempts from 28 IPs since September 19, 2026, with 333 starting October 11 and 316 on October 15. Attackers logged in with common credentials, then exfiltrated `LANGFLOW_SECRET_KEY` and `LANGFLOW_SUPERUSER_PASSWORD` and tried Docker host filesystem access. GreyNoise links one source IP to earlier Langflow and Flowise exploitation. CVSS 9.9. Exploitation figures are single source
Root cause
User-supplied MCP server commands passed to a shell with no allowlist or sandbox, available to every authenticated role
CVE
Sources
Catalog
Cite this: AgentProv incident record: Langflow MCP stdio RCE Exploited in the Wild: 1,706 Attempts Steal Secret Keys and Superuser Passwords (CVE-2026-105740) (2026-10-15). https://agentprov.com/incidents/2026-10-15-langflow-mcp-stdio-rce-exploited-in-the-wild-1-706-attempts-steal-secret-keys
Related
- Also L5 · 2026-10-25Planted AGENTS.md in a Downloads Folder Got Codex to Install Malware; a CLAUDE.md Variant Exposed Claude Code's OAuth TokenL5Config
- Also L5 · 2026-10-21MCP Inspector Advisory Batch: Two Critical Paths From Connecting to a Malicious MCP Server to Local Command ExecutionL5Config
- Also L5 · 2026-10-16Claude Agent SDK: A Crafted Session ID Injects an MCP Server and Runs Commands Past SDK Permissions (CVE-2026-96620)L5Config