CVE-2026-31951 (GCVE-0-2026-31951)
Vulnerability from cvelistv5 – Published: 2026-03-27 19:29 – Updated: 2026-03-31 13:46
VLAI
EPSS
VEX
Title
LibreChat's MCP Server Header Injection Enables OAuth Token Theft
Summary
LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue.
Severity
6.8 (Medium)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-03-31 13:45 UTC
CWE
- CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/danny-avila/LibreChat/security… | x_refsource_CONFIRM |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| danny-avila | LibreChat |
Affected:
>= v0.8.2-rc1, <= v0.8.3-rc1
|
guessed |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-31951",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-31T13:45:16.896153Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-03-31T13:46:25.297Z",
"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-rc1, \u003c= v0.8.3-rc1"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.8,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/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": "2026-03-27T19:29:25.892Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954"
}
],
"source": {
"advisory": "GHSA-pmw7-gqwj-f954",
"discovery": "UNKNOWN"
},
"title": "LibreChat\u0027s MCP Server Header Injection Enables OAuth Token Theft"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-31951",
"datePublished": "2026-03-27T19:29:25.892Z",
"dateReserved": "2026-03-10T15:10:10.657Z",
"dateUpdated": "2026-03-31T13:46:25.297Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-31951",
"date": "2026-09-19",
"epss": "0.00244",
"percentile": "0.15899"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "LibreChat",
"vendor": "danny-avila",
"versions": [
{
"status": "affected",
"version": "\u003e= v0.8.2-rc1, \u003c= v0.8.3-rc1"
}
]
}
],
"source": "security-advisories@github.com"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:librechat:librechat:*:*:*:*:*:*:*:*",
"matchCriteriaId": "0B0F03AD-B51B-4501-B292-3133DBD964A8",
"versionEndExcluding": "0.8.3",
"versionStartIncluding": "0.8.2",
"vulnerable": true
},
{
"criteria": "cpe:2.3:a:librechat:librechat:0.8.3:rc1:*:*:*:*:*:*",
"matchCriteriaId": "482D0FE3-2AB3-47B6-982E-564A5B824464",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue."
}
],
"id": "CVE-2026-31951",
"lastModified": "2026-06-17T10:34:49.693",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.8,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N",
"version": "3.1"
},
"exploitabilityScore": 2.3,
"impactScore": 4.0,
"source": "security-advisories@github.com",
"type": "Secondary"
},
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 5.7,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:N/A:N",
"version": "3.1"
},
"exploitabilityScore": 2.1,
"impactScore": 3.6,
"source": "nvd@nist.gov",
"type": "Primary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-31951",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-31T13:45:16.896153Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-03-27T20:16:30.397",
"references": [
{
"source": "security-advisories@github.com",
"tags": [
"Exploit",
"Vendor Advisory"
],
"url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-200"
}
],
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"current_release_date": "2026-03-28T23:09:47+00:00",
"cve": "CVE-2026-31951",
"id": "CVE-2026-31951",
"initial_release_date": "2026-01-01T00:00:00+00:00",
"product_status:known_not_affected": "1",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "LibreChat\u0027s MCP Server Header Injection Enables OAuth Token Theft",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-31951.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-31951",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-31T13:45:16.896153Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-03-31T13:46:22.158Z",
"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-rc1, \u003c= v0.8.3-rc1"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.8,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/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": "2026-03-27T19:29:25.892Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954"
}
],
"source": {
"advisory": "GHSA-pmw7-gqwj-f954",
"discovery": "UNKNOWN"
},
"title": "LibreChat\u0027s MCP Server Header Injection Enables OAuth Token Theft"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-31951",
"datePublished": "2026-03-27T19:29:25.892Z",
"dateReserved": "2026-03-10T15:10:10.657Z",
"dateUpdated": "2026-03-31T13:46:25.297Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
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…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
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.
Loading…