CVE-2026-105697 (GCVE-0-2026-105697)

Vulnerability from cvelistv5 – Published: 2026-10-05 20:16 – Updated: 2026-10-05 20:16
VLAI
Title
Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration
Summary
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.
Severity
9.9 (Critical)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
CWE
  • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Assigner
References
Impacted products
Vendor Product Version CPE status
langflow-ai langflow Affected: >= 1.1.2, < 1.10.3
guessed Create a notification for this product.
langflow-ai langflow-base Affected: >= 0.1.2, < 0.10.3
guessed Create a notification for this product.
langflow-ai lfx Affected: < 1.10.3
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "cna": {
      "affected": [
        {
          "product": "langflow",
          "vendor": "langflow-ai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 1.1.2, \u003c 1.10.3"
            }
          ]
        },
        {
          "product": "langflow-base",
          "vendor": "langflow-ai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.1.2, \u003c 0.10.3"
            }
          ]
        },
        {
          "product": "lfx",
          "vendor": "langflow-ai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.10.3"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "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 \u2192 MCP Servers \u2192 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) \u2014 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."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.9,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-78",
              "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-05T20:16:58.291Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45"
        },
        {
          "name": "https://github.com/langflow-ai/langflow/pull/12290",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/langflow-ai/langflow/pull/12290"
        },
        {
          "name": "https://github.com/langflow-ai/langflow/pull/14036",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/langflow-ai/langflow/pull/14036"
        },
        {
          "name": "https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d"
        },
        {
          "name": "https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0"
        },
        {
          "name": "https://github.com/langflow-ai/langflow/releases/tag/v1.10.3",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/langflow-ai/langflow/releases/tag/v1.10.3"
        }
      ],
      "source": {
        "advisory": "GHSA-w794-rj3p-xv45",
        "discovery": "UNKNOWN"
      },
      "title": "Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-105697",
    "datePublished": "2026-10-05T20:16:58.291Z",
    "dateReserved": "2026-10-05T17:48:58.627Z",
    "dateUpdated": "2026-10-05T20:16:58.291Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "langflow",
                "vendor": "langflow-ai",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003e= 1.1.2, \u003c 1.10.3"
                  }
                ]
              },
              {
                "product": "langflow-base",
                "vendor": "langflow-ai",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003e= 0.1.2, \u003c 0.10.3"
                  }
                ]
              },
              {
                "product": "lfx",
                "vendor": "langflow-ai",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 1.10.3"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "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 \u2192 MCP Servers \u2192 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) \u2014 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."
          }
        ],
        "id": "CVE-2026-105697",
        "lastModified": "2026-10-05T21:16:35.087",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.9,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 3.1,
              "impactScore": 6.0,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ]
        },
        "published": "2026-10-05T21:16:35.087",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langflow-ai/langflow/pull/12290"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langflow-ai/langflow/pull/14036"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langflow-ai/langflow/releases/tag/v1.10.3"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Received",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-78"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Primary"
          }
        ]
      }
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.



Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.