CVE-2026-31944 (GCVE-0-2026-31944)

Vulnerability from cvelistv5 – Published: 2026-03-13 19:44 – Updated: 2026-03-16 13:41
VLAI?
Title
LibreChat MCP OAuth callback does not validate browser session — allows token theft via redirect link
Summary
LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redirect URL is logged in or that the logged-in user matches the initiator. An attacker can send the authorization URL to a victim; when the victim completes the flow, the victim’s OAuth tokens are stored on the attacker’s LibreChat account, enabling account takeover of the victim’s MCP-linked services (e.g. Atlassian, Outlook). This vulnerability is fixed in 0.8.3-rc1.
Severity ?
7.6 (High)
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N
CWE
  • CWE-306 - Missing Authentication for Critical Function
Assigner
References
Impacted products
Vendor Product Version
danny-avila LibreChat Affected: >= v0.8.2, <= 0.8.2-rc3
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-31944",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-03-16T13:40:08.924691Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-03-16T13:41:21.254Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "LibreChat",
          "vendor": "danny-avila",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= v0.8.2, \u003c= 0.8.2-rc3"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redirect URL is logged in or that the logged-in user matches the initiator. An attacker can send the authorization URL to a victim; when the victim completes the flow, the victim\u2019s OAuth tokens are stored on the attacker\u2019s LibreChat account, enabling account takeover of the victim\u2019s MCP-linked services (e.g. Atlassian, Outlook). This vulnerability is fixed in 0.8.3-rc1."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 7.6,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "LOW",
            "privilegesRequired": "LOW",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-306",
              "description": "CWE-306: Missing Authentication for Critical Function",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-03-13T19:44:30.850Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vf7j-7mrx-hp7g",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vf7j-7mrx-hp7g"
        }
      ],
      "source": {
        "advisory": "GHSA-vf7j-7mrx-hp7g",
        "discovery": "UNKNOWN"
      },
      "title": "LibreChat MCP OAuth callback does not validate browser session \u2014 allows token theft via redirect link"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-31944",
    "datePublished": "2026-03-13T19:44:30.850Z",
    "dateReserved": "2026-03-10T15:10:10.656Z",
    "dateUpdated": "2026-03-16T13:41:21.254Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-31944\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-03-13T19:54:39.590\",\"lastModified\":\"2026-03-16T14:54:11.293\",\"vulnStatus\":\"Undergoing Analysis\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redirect URL is logged in or that the logged-in user matches the initiator. An attacker can send the authorization URL to a victim; when the victim completes the flow, the victim\u2019s OAuth tokens are stored on the attacker\u2019s LibreChat account, enabling account takeover of the victim\u2019s MCP-linked services (e.g. Atlassian, Outlook). This vulnerability is fixed in 0.8.3-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:R/S:C/C:H/I:L/A:N\",\"baseScore\":7.6,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"REQUIRED\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"LOW\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.3,\"impactScore\":4.7}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-306\"}]}],\"references\":[{\"url\":\"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vf7j-7mrx-hp7g\",\"source\":\"security-advisories@github.com\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-31944\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-03-16T13:40:08.924691Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-03-16T13:41:15.558Z\"}}], \"cna\": {\"title\": \"LibreChat MCP OAuth callback does not validate browser session \\u2014 allows token theft via redirect link\", \"source\": {\"advisory\": \"GHSA-vf7j-7mrx-hp7g\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 7.6, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:L/A:N\", \"integrityImpact\": \"LOW\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"danny-avila\", \"product\": \"LibreChat\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= v0.8.2, \u003c= 0.8.2-rc3\"}]}], \"references\": [{\"url\": \"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vf7j-7mrx-hp7g\", \"name\": \"https://github.com/danny-avila/LibreChat/security/advisories/GHSA-vf7j-7mrx-hp7g\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP (Model Context Protocol) OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redirect URL is logged in or that the logged-in user matches the initiator. An attacker can send the authorization URL to a victim; when the victim completes the flow, the victim\\u2019s OAuth tokens are stored on the attacker\\u2019s LibreChat account, enabling account takeover of the victim\\u2019s MCP-linked services (e.g. Atlassian, Outlook). This vulnerability is fixed in 0.8.3-rc1.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-306\", \"description\": \"CWE-306: Missing Authentication for Critical Function\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-03-13T19:44:30.850Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-31944\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-03-16T13:41:21.254Z\", \"dateReserved\": \"2026-03-10T15:10:10.656Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-03-13T19:44:30.850Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

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.