# Langflow MCP-config RCE (GHSA-7w94-79vh-5mr2, GHSA-w794-rj3p-xv45)

- ID: langflow-mcp-rce-ghsa-2026
- Reported: 2026-10-11
- Researcher: Adam-Aghili, andifilhohub, Previdian
- Organization: Langflow, Previdian
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-04
- Entry page: https://openattacks.ai/attacks/langflow-mcp-rce-ghsa-2026/
- Entry JSON: https://openattacks.ai/api/attacks/langflow-mcp-rce-ghsa-2026.json
- Browse title: Langflow MCP-config RCE (GHSA-7w94-79vh-5mr2, GHSA-w794-rj3p-xv45)
- Editorial summary: GHSA-7w94-79vh-5mr2 (CVE-2026-105697) and GHSA-w794-rj3p-xv45: Authenticated Langflow users can achieve RCE by adding MCP server with Stdio transport. User-supplied command field passed directly to bash -c…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/langflow-mcp-rce-ghsa-2026.json

## Technique
GHSA-7w94-79vh-5mr2 (CVE-2026-105697) and GHSA-w794-rj3p-xv45: Authenticated Langflow users can achieve RCE by adding MCP server with Stdio transport. User-supplied command field passed directly to bash -c 'exec \{command\}' with zero validation, no allowlisting, no sandboxing. Env field allows arbitrary environment variable injection (LD\_PRELOAD, PATH override). Command executes when server list fetched with action\_count=true - happens automatically in UI MCP settings page. Affects \<1.9.0 (GHSA-7w94-79vh-5mr2) and \<1.10.3 (GHSA-w794-rj3p-xv45). Default LANGFLOW\_AUTO\_LOGIN=true hands out token without credentials. Previdian honeypots recorded 1,423 exploitation attempts from 27 IPs (Belgium, China, Germany, Hong Kong, Japan, Nigeria, Philippines, Russia, Seychelles, Singapore, South Korea, Taiwan, Tanzania, US, Vietnam) beginning Sep 19, 2026. Attackers first checked auto-login, then brute-forced credentials. Fixed in 1.9.0 (command allowlist) and 1.10.3 (full policy enforcement, removed bash wrapper). GitHub: github.com/langflow-ai/langflow.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Authenticated user access (or LANGFLOW\_AUTO\_LOGIN=true provides token without credentials); exploitation via POST/PATCH /api/v2/mcp/servers/\{server\_name\} or embedded flow configs

## AI tooling and models
- Langflow AI workflow platform
- Model Context Protocol (MCP) Stdio transport

## Other tooling
- bash command execution
- Environment variable injection (LD\_PRELOAD, NODE\_OPTIONS, PYTHONPATH, BASH\_ENV)

## Victims and sectors
Langflow installations; multiple internet-facing vulnerable instances found; 1,423 exploitation attempts against Previdian honeypots from 27 countries

## Target geography
- Multiple regions

## Attribution
Multiple attackers from 27 countries; financially motivated/opportunistic exploitation

## Scale and metrics
1,423 exploitation attempts against Previdian honeypots from 27 IPs (Sep 19-Oct 2026); 333 attempts on Oct 11 alone; first attempts Sep 19 (2+ weeks before CVE publication Oct 5); dramatic increase post-CVE

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### auth: Obtain authentication [access]
Default LANGFLOW\_AUTO\_LOGIN=true provides token without credentials via GET /api/v1/auto\_login; or brute-force credentials if auto-login disabled
Evidence: https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45

### inject-command: Add malicious MCP server [ai]
POST/PATCH /api/v2/mcp/servers/\{server\_name\} with Stdio transport; command field contains arbitrary OS command (reverse shell, file operations, etc.); env field can inject LD\_PRELOAD, PATH override
Evidence: https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2

### trigger: Trigger execution [execution]
Command executes automatically when GET /api/v2/mcp/servers?action\_count=true (happens when anyone navigates to MCP settings page); re-executes every time list loaded; persistent backdoor
Evidence: https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2

### rce: Remote code execution [impact]
User-supplied command wrapped in bash -c 'exec \{command\}' and executed; no validation, allowlisting, or sandboxing; runs with Langflow process privileges; full server compromise possible
Evidence: https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2

Connections:
- auth -> inject-command
- inject-command -> trigger
- trigger -> rce

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### auth: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### inject-command: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### trigger: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### rce: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0034: Cost Harvesting — Exploitation of vulnerability in AI workflow platform (Langflow) via MCP server misconfiguration
  Technique: https://atlas.mitre.org/techniques/AML.T0034
  Evidence: https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2

## Defensive notes
Upgrade to Langflow 1.10.3+; disable LANGFLOW\_AUTO\_LOGIN; enforce strong unique passwords; review MCP server configurations; monitor /api/v2/mcp/servers/ API access; check for unexpected command/env entries; network segmentation; principle of least privilege

## Sources
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2 — GHSA-7w94-79vh-5mr2: Authenticated RCE via MCP Stdio transport
- https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45 — GHSA-w794-rj3p-xv45: OS command injection RCE via MCP stdio
- https://thehackernews.com/2026/10/langflows-critical-authenticated-rce.html — Langflow Critical Authenticated RCE Flaw Targeted
- https://www.vulncheck.com/blog/pwning-the-ai-stack — VulnCheck - Pwning the AI Stack

## Source notes
Two GitHub Security Advisories (GHSA-7w94-79vh-5mr2 for \<1.9.0, GHSA-w794-rj3p-xv45 for \<1.10.3); Previdian observed exploitation 2+ weeks before public CVE; VulnCheck analysis of AI stack vulnerabilities. Detection: monitor Langflow API /api/v2/mcp/servers/ for suspicious commands, review MCP Stdio configs, check for bash -c execution, monitor env var injection patterns (LD\_PRELOAD, PATH), alert on auto-login token requests from unexpected IPs.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
