Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
Langflow (PyPI packages langflow, langflow-base and lfx) is vulnerable to OS command injection through MCP stdio server configurations: langflow 1.1.2 to before 1.10.3, langflow-base 0.1.2 to before 0.10.3, and lfx before 1.10.3. An attacker who can reach the MCP server settings or build a flow with an MCP Tools component can supply an arbitrary command that runs on the Langflow host as the process user. With the default auto-login setting, no account is needed. Upgrade to langflow 1.10.3, langflow-base 0.10.3 or lfx 1.10.3.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 9.9 | Critical | 3.1 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0095, the 61st percentile, on 8 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:08 UTC First seen by agentprime
- 31 Oct 2026, 14:08 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-w794-rj3p-xv45
- OSV: GHSA-w794-rj3p-xv45
- github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2
- github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45
- nvd.nist.gov/vuln/detail/CVE-2026-105697
- github.com/langflow-ai/langflow/pull/12290
- github.com/langflow-ai/langflow/pull/14036
- github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d
- github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0
- github.com/langflow-ai/langflow
- github.com/langflow-ai/langflow/releases/tag/v1.10.3
- www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem
- www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp