CVE-2026-32625 (GCVE-0-2026-32625)

Vulnerability from cvelistv5 – Published: 2026-06-02 22:35 – Updated: 2026-06-03 14:07
VLAI
Title
LibreChat Exfiltrates Server Secrets via MCP Server URL Injection
Summary
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker's server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation's cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.
Severity
9.6 (Critical)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N
SSVC
Exploitation: poc Automatable: no Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
  • CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor
Assigner
References
Impacted products
Vendor Product Version
danny-avila LibreChat Affected: < 0.8.4-rc1
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-32625",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-03T13:28:03.174610Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-03T14:07:46.872Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "LibreChat",
          "vendor": "danny-avila",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.8.4-rc1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server\u0027s process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker\u0027s server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation\u0027s cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 9.6,
            "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:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-200",
              "description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-06-02T22:35:00.859Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx"
        }
      ],
      "source": {
        "advisory": "GHSA-4pcc-j6m6-wcwx",
        "discovery": "UNKNOWN"
      },
      "title": "LibreChat Exfiltrates Server Secrets via MCP Server URL Injection"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-32625",
    "datePublished": "2026-06-02T22:35:00.859Z",
    "dateReserved": "2026-03-12T15:29:36.558Z",
    "dateUpdated": "2026-06-03T14:07:46.872Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-32625",
      "date": "2026-06-03",
      "epss": "0.00031",
      "percentile": "0.09201"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-32625\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-06-02T23:16:35.947\",\"lastModified\":\"2026-06-03T16:16:27.873\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server\u0027s process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker\u0027s server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation\u0027s cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.\"}],\"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:N\",\"baseScore\":9.6,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":3.1,\"impactScore\":5.8}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-200\"}]}],\"references\":[{\"url\":\"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-32625\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-06-03T13:28:03.174610Z\"}}}], \"references\": [{\"url\": \"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-06-03T13:28:23.626Z\"}}], \"cna\": {\"title\": \"LibreChat Exfiltrates Server Secrets via MCP Server URL Injection\", \"source\": {\"advisory\": \"GHSA-4pcc-j6m6-wcwx\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 9.6, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"danny-avila\", \"product\": \"LibreChat\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.8.4-rc1\"}]}], \"references\": [{\"url\": \"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx\", \"name\": \"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-4pcc-j6m6-wcwx\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server\u0027s process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker\u0027s server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation\u0027s cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-200\", \"description\": \"CWE-200: Exposure of Sensitive Information to an Unauthorized Actor\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-06-02T22:35:00.859Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-32625\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-06-03T14:07:46.872Z\", \"dateReserved\": \"2026-03-12T15:29:36.558Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-06-02T22:35:00.859Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


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.


Detection rules are retrieved from Rulezet.