CVE-2026-44450 (GCVE-0-2026-44450)

Vulnerability from cvelistv5 – Published: 2026-05-26 19:54 – Updated: 2026-06-01 17:09
VLAI
Title
Lumiverse: RCE via MCP stdio argument injection
Summary
Lumiverse is a full-featured AI chat application. Prior to 0.9.7, the MCP server creation endpoint validates the command field against an allowlist of binary names but forwards the args array to the child process without any validation. Every binary on the allowlist accepts an inline-code execution flag (-e for node/bun, -c for python3/deno), giving any logged-in user arbitrary OS-level code execution on the Lumiverse server. The route requires only requireAuth (not requireOwner). The server binds on all interfaces (::) and the host-header rebinding check is bypassed trivially by any HTTP client that sends Host: localhost:<port> directly, making this exploitable from any machine with network access to the server port. This vulnerability is fixed in 0.9.7.
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
  • CWE-88 - Improper Neutralization of Argument Delimiters in a Command ('Argument Injection')
Assigner
References
Impacted products
Vendor Product Version
prolix-oc Lumiverse Affected: < 0.9.7
Create a notification for this product.
Show details on NVD website

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44450",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-01T17:03:56.285972Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-01T17:09:40.653Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "Lumiverse",
          "vendor": "prolix-oc",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.9.7"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Lumiverse is a full-featured AI chat application. Prior to 0.9.7, the MCP server creation endpoint validates the command field against an allowlist of binary names but forwards the args array to the child process without any validation. Every binary on the allowlist accepts an inline-code execution flag (-e for node/bun, -c for python3/deno), giving any logged-in user arbitrary OS-level code execution on the Lumiverse server. The route requires only requireAuth (not requireOwner). The server binds on all interfaces (::) and the host-header rebinding check is bypassed trivially by any HTTP client that sends Host: localhost:\u003cport\u003e directly, making this exploitable from any machine with network access to the server port. This vulnerability is fixed in 0.9.7."
        }
      ],
      "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-88",
              "description": "CWE-88: Improper Neutralization of Argument Delimiters in a Command (\u0027Argument Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-26T19:54:33.944Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/prolix-oc/Lumiverse/security/advisories/GHSA-mfwv-ch2f-9j5v",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/prolix-oc/Lumiverse/security/advisories/GHSA-mfwv-ch2f-9j5v"
        }
      ],
      "source": {
        "advisory": "GHSA-mfwv-ch2f-9j5v",
        "discovery": "UNKNOWN"
      },
      "title": "Lumiverse: RCE via MCP stdio argument injection"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-44450",
    "datePublished": "2026-05-26T19:54:33.944Z",
    "dateReserved": "2026-05-06T15:49:25.192Z",
    "dateUpdated": "2026-06-01T17:09:40.653Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-44450",
      "date": "2026-07-23",
      "epss": "0.00377",
      "percentile": "0.30179"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-44450\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-26T21:16:38.173\",\"lastModified\":\"2026-07-23T11:10:00.120\",\"vulnStatus\":\"Deferred\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Lumiverse is a full-featured AI chat application. Prior to 0.9.7, the MCP server creation endpoint validates the command field against an allowlist of binary names but forwards the args array to the child process without any validation. Every binary on the allowlist accepts an inline-code execution flag (-e for node/bun, -c for python3/deno), giving any logged-in user arbitrary OS-level code execution on the Lumiverse server. The route requires only requireAuth (not requireOwner). The server binds on all interfaces (::) and the host-header rebinding check is bypassed trivially by any HTTP client that sends Host: localhost:\u003cport\u003e directly, making this exploitable from any machine with network access to the server port. This vulnerability is fixed in 0.9.7.\"},{\"lang\":\"es\",\"value\":\"Lumiverse es una aplicaci\u00f3n de chat de IA con todas las funciones. Antes de la 0.9.7, el endpoint de creaci\u00f3n del servidor MCP valida el campo de comando contra una lista de permitidos de nombres de binarios, pero reenv\u00eda el array de argumentos al proceso hijo sin ninguna validaci\u00f3n. Cada binario en la lista de permitidos acepta un flag de ejecuci\u00f3n de c\u00f3digo en l\u00ednea (-e para node/bun, -c para python3/deno), otorgando a cualquier usuario autenticado la ejecuci\u00f3n arbitraria de c\u00f3digo a nivel de sistema operativo en el servidor Lumiverse. La ruta solo requiere requireAuth (no requireOwner). El servidor se enlaza a todas las interfaces (::) y la verificaci\u00f3n de re-enlace del encabezado Host se omite trivialmente por cualquier cliente HTTP que env\u00ede Host: localhost:\u003cport\u003e directamente, haciendo esto explotable desde cualquier m\u00e1quina con acceso de red al puerto del servidor. Esta vulnerabilidad se corrigi\u00f3 en la 0.9.7.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"prolix-oc\",\"product\":\"Lumiverse\",\"versions\":[{\"version\":\"\u003c 0.9.7\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H\",\"baseScore\":9.9,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.1,\"impactScore\":6.0}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-06-01T17:03:56.285972Z\",\"id\":\"CVE-2026-44450\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-88\"}]}],\"references\":[{\"url\":\"https://github.com/prolix-oc/Lumiverse/security/advisories/GHSA-mfwv-ch2f-9j5v\",\"source\":\"security-advisories@github.com\"}]}}",
    "redhat_vex": {
      "current_release_date": "2026-06-01T22:03:27+00:00",
      "cve": "CVE-2026-44450",
      "id": "CVE-2026-44450",
      "initial_release_date": "2026-01-01T00:00:00+00:00",
      "product_status:known_not_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "Lumiverse: RCE via MCP stdio argument injection",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-44450.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-44450\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-06-01T17:03:56.285972Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-06-01T17:09:35.521Z\"}}], \"cna\": {\"title\": \"Lumiverse: RCE via MCP stdio argument injection\", \"source\": {\"advisory\": \"GHSA-mfwv-ch2f-9j5v\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 9.9, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"prolix-oc\", \"product\": \"Lumiverse\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.9.7\"}]}], \"references\": [{\"url\": \"https://github.com/prolix-oc/Lumiverse/security/advisories/GHSA-mfwv-ch2f-9j5v\", \"name\": \"https://github.com/prolix-oc/Lumiverse/security/advisories/GHSA-mfwv-ch2f-9j5v\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Lumiverse is a full-featured AI chat application. Prior to 0.9.7, the MCP server creation endpoint validates the command field against an allowlist of binary names but forwards the args array to the child process without any validation. Every binary on the allowlist accepts an inline-code execution flag (-e for node/bun, -c for python3/deno), giving any logged-in user arbitrary OS-level code execution on the Lumiverse server. The route requires only requireAuth (not requireOwner). The server binds on all interfaces (::) and the host-header rebinding check is bypassed trivially by any HTTP client that sends Host: localhost:\u003cport\u003e directly, making this exploitable from any machine with network access to the server port. This vulnerability is fixed in 0.9.7.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-88\", \"description\": \"CWE-88: Improper Neutralization of Argument Delimiters in a Command (\u0027Argument Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-26T19:54:33.944Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-44450\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-06-01T17:09:40.653Z\", \"dateReserved\": \"2026-05-06T15:49:25.192Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-26T19:54:33.944Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

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.

Loading…

Detection rules are retrieved from Rulezet.

Loading…

Loading…

Loading…