CVE-2026-105697: Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration
Advisory generated from the CVE record, CISA, Exploit Observer and VEDAS: what it is, whether it is exploited, who is affected, and how to fix and detect it.
Generated by VEDAS. Scores as of 2026-11-08 00:03 UTC. Rebuilt every few hours from cve-scores, CISA KEV and vedas-signatures. How this works and its limits.
What it is
Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c “exec {command} ...”. Any user able to reach the MCP server settings (“Settings → MCP Servers → Add MCP Server”, POST/PATCH /api/v2/mcp/servers/{server_name}) or to build a flow with the MCP Tools component could add a “server” whose command is an arbitrary OS command (touch, rm -rf, a reverse shell, ...). The command runs on the Langflow host as the Langflow process user as soon as Langflow tries to connect to the server (listing servers, loading tools, running the flow), even when the UI then reports that the stdio server failed to start. With the default LANGFLOW_AUTO_LOGIN=true, GET /api/v1/auto_login hands out a token without credentials, so on an exposed instance running the default configuration this is reachable without an account. AUTO_LOGIN is documented as a development-only setting; with it disabled, any authenticated (non-admin) user can exploit it. This issue is fixed in Langflow 1.10.3, langflow-base 0.10.3, and lfx 1.10.3.
Description quoted from the CVE record (assigned by GitHub_M, published 2026-10-05).
Weakness: CWE-78: Improper Neutralization of Special Elements used in an OS Command (‘OS Command Injection’)
How it can be exploited
Exploitable over the network with low attack complexity needing low privileges and no user interaction. Impact: confidentiality high, integrity high, availability high. CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
CISA assessment (SSVC): CISA has no evidence of exploitation. Automatable: no. Technical impact: total.
Public exploit evidence (Exploit Observer)
Exploit Observer found 3 code repositories naming this CVE.
Code repositories that name a CVE are often scanners, copies or fakes, and some are malware. Read the code before running anything.
See all 8 references on Exploit Observer
Live scores
- EPSS
- 0.009
low predicted chance of attack - VEDAS
- 0.985
strong exploit evidence - On CISA KEV
- Not listed
- Detection rule
- Suricata
Who is affected
| Product | Affected | Not affected |
|---|---|---|
| langflow-ai langflow | version >= 1.1.2, < 1.10.3 | Not stated |
| langflow-ai langflow-base | version >= 0.1.2, < 0.10.3 | Not stated |
| langflow-ai lfx | version < 1.10.3 | Not stated |
Version ranges exactly as the CVE record states them. “Before X” means X is the first fixed version.
How to fix it
No fixed version or vendor advisory is listed in the CVE record yet. Watch the vendor’s security page.
How to detect it
Suricata rules (network detection)
1 rule that alert on traffic matching this exploit: VEDAS CVE-2026-105697 Langflow - Remote Code Execution via MCP stdio Server Command. Add them to your Suricata rule set and reload.
Show the rules
alert http $EXTERNAL_NET any -> $HTTP_SERVERS $HTTP_PORTS (msg:"VEDAS CVE-2026-105697 Langflow - Remote Code Execution via MCP stdio Server Command"; flow:established,to_server; http.uri; content:"/api/v2/mcp/servers"; nocase; fast_pattern; http.request_body; content:"command"; nocase; classtype:attempted-admin; reference:cve,CVE-2026-105697; reference:url,https://www.exploit.observer/?keyword=CVE-2026-105697&match=exact; reference:url,https://subdomain.center/?engine=ammonites&keyword=langflow&match=exact; sid:1104405; rev:1;)
CVE-2026-105697.rules on GitHub
References
Other references
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45 (x_refsource_CONFIRM)
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2 (x_refsource_MISC)
- https://github.com/langflow-ai/langflow/pull/12290 (x_refsource_MISC)
- https://github.com/langflow-ai/langflow/pull/14036 (x_refsource_MISC)
- https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d (x_refsource_MISC)
- https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0 (x_refsource_MISC)
- https://github.com/langflow-ai/langflow/releases/tag/v1.10.3 (x_refsource_MISC)
- https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem (x_refsource_MISC)
- https://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp (x_refsource_MISC)
Other databases
Where this comes from
This advisory is generated automatically by VEDAS from: CVE.org record, cve-scores (EPSS and VEDAS), Exploit Observer, vedas-signatures. Text in quotes is reproduced from the source; everything else is a fixed template filled with source fields. Nothing here is written by a language model. Check the vendor advisory before acting, and read how VEDAS and Exploit Observer work, and their limits.
Supporting partners
