CVE-2026-84377 (GCVE-0-2026-84377)
Vulnerability from cvelistv5 – Published: 2026-09-02 17:18 – Updated: 2026-09-03 14:31
VLAI
EPSS
VEX
Title
LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters
Summary
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials to that destination. Request validation in litellm/proxy/auth/auth_utils.py, litellm/proxy/common_request_processing.py, litellm/proxy/health_endpoints/_health_endpoints.py, litellm/proxy/image_endpoints/endpoints.py, and litellm/proxy/litellm_pre_call_utils.py used incomplete checks that did not cover every sensitive parameter or inspect equivalent values across nested request fields, path values, and bracket-notation form data. Routing and credential parameters including api_base, base_url, model_list, fallbacks, and litellm_credential_name could therefore be applied without clearing the operator's stored key, exposing upstream provider credentials and other configured secrets and permitting server-side requests to internal services reachable by the proxy. This issue is fixed in versions 1.88.6 and 1.96.2.
Severity
6.5 (Medium)
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-03 14:06 UTC
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
9 references
| URL | Tags |
|---|---|
| https://github.com/BerriAI/litellm/security/advis… | x_refsource_CONFIRM |
| https://github.com/BerriAI/litellm/pull/36011 | x_refsource_MISC |
| https://github.com/BerriAI/litellm/pull/36314 | x_refsource_MISC |
| https://github.com/BerriAI/litellm/pull/36494 | x_refsource_MISC |
| https://github.com/BerriAI/litellm/commit/473f72e… | x_refsource_MISC |
| https://github.com/BerriAI/litellm/commit/820f247… | x_refsource_MISC |
| https://github.com/BerriAI/litellm/commit/c898d34… | x_refsource_MISC |
| https://github.com/BerriAI/litellm/releases/tag/v1.88.6 | x_refsource_MISC |
| https://github.com/BerriAI/litellm/releases/tag/v1.96.2 | x_refsource_MISC |
Impacted products
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-84377",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-03T14:06:05.318151Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-03T14:31:30.548Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "litellm",
"vendor": "BerriAI",
"versions": [
{
"status": "affected",
"version": "\u003c 1.88.6"
},
{
"status": "affected",
"version": "\u003e= 1.89.0, \u003c 1.96.2"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials to that destination. Request validation in litellm/proxy/auth/auth_utils.py, litellm/proxy/common_request_processing.py, litellm/proxy/health_endpoints/_health_endpoints.py, litellm/proxy/image_endpoints/endpoints.py, and litellm/proxy/litellm_pre_call_utils.py used incomplete checks that did not cover every sensitive parameter or inspect equivalent values across nested request fields, path values, and bracket-notation form data. Routing and credential parameters including api_base, base_url, model_list, fallbacks, and litellm_credential_name could therefore be applied without clearing the operator\u0027s stored key, exposing upstream provider credentials and other configured secrets and permitting server-side requests to internal services reachable by the proxy. This issue is fixed in versions 1.88.6 and 1.96.2."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-02T17:18:32.728Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/BerriAI/litellm/security/advisories/GHSA-3cv6-jpf6-8222",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/BerriAI/litellm/security/advisories/GHSA-3cv6-jpf6-8222"
},
{
"name": "https://github.com/BerriAI/litellm/pull/36011",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/BerriAI/litellm/pull/36011"
},
{
"name": "https://github.com/BerriAI/litellm/pull/36314",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/BerriAI/litellm/pull/36314"
},
{
"name": "https://github.com/BerriAI/litellm/pull/36494",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/BerriAI/litellm/pull/36494"
},
{
"name": "https://github.com/BerriAI/litellm/commit/473f72e63a9777d793fbbf57194d8ec4fb97bc1b",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/BerriAI/litellm/commit/473f72e63a9777d793fbbf57194d8ec4fb97bc1b"
},
{
"name": "https://github.com/BerriAI/litellm/commit/820f247a6abba55cd87d130bef7bba7be3b29d37",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/BerriAI/litellm/commit/820f247a6abba55cd87d130bef7bba7be3b29d37"
},
{
"name": "https://github.com/BerriAI/litellm/commit/c898d341c02299cf2506d0d8e84cc67953043593",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/BerriAI/litellm/commit/c898d341c02299cf2506d0d8e84cc67953043593"
},
{
"name": "https://github.com/BerriAI/litellm/releases/tag/v1.88.6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/BerriAI/litellm/releases/tag/v1.88.6"
},
{
"name": "https://github.com/BerriAI/litellm/releases/tag/v1.96.2",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/BerriAI/litellm/releases/tag/v1.96.2"
}
],
"source": {
"advisory": "GHSA-3cv6-jpf6-8222",
"discovery": "UNKNOWN"
},
"title": "LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-84377",
"datePublished": "2026-09-02T17:18:32.728Z",
"dateReserved": "2026-09-01T16:27:58.129Z",
"dateUpdated": "2026-09-03T14:31:30.548Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-84377",
"date": "2026-09-03",
"epss": "0.00313",
"percentile": "0.23663"
},
"nvd": "{\"cve\":{\"id\":\"CVE-2026-84377\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-09-02T18:21:28.997\",\"lastModified\":\"2026-09-03T15:17:35.120\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials to that destination. Request validation in litellm/proxy/auth/auth_utils.py, litellm/proxy/common_request_processing.py, litellm/proxy/health_endpoints/_health_endpoints.py, litellm/proxy/image_endpoints/endpoints.py, and litellm/proxy/litellm_pre_call_utils.py used incomplete checks that did not cover every sensitive parameter or inspect equivalent values across nested request fields, path values, and bracket-notation form data. Routing and credential parameters including api_base, base_url, model_list, fallbacks, and litellm_credential_name could therefore be applied without clearing the operator\u0027s stored key, exposing upstream provider credentials and other configured secrets and permitting server-side requests to internal services reachable by the proxy. This issue is fixed in versions 1.88.6 and 1.96.2.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"BerriAI\",\"product\":\"litellm\",\"versions\":[{\"version\":\"\u003c 1.88.6\",\"status\":\"affected\"},{\"version\":\"\u003e= 1.89.0, \u003c 1.96.2\",\"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:U/C:H/I:N/A:N\",\"baseScore\":6.5,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":3.6}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-09-03T14:06:05.318151Z\",\"id\":\"CVE-2026-84377\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"partial\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"references\":[{\"url\":\"https://github.com/BerriAI/litellm/commit/473f72e63a9777d793fbbf57194d8ec4fb97bc1b\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/commit/820f247a6abba55cd87d130bef7bba7be3b29d37\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/commit/c898d341c02299cf2506d0d8e84cc67953043593\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/pull/36011\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/pull/36314\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/pull/36494\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/releases/tag/v1.88.6\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/releases/tag/v1.96.2\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/security/advisories/GHSA-3cv6-jpf6-8222\",\"source\":\"security-advisories@github.com\"}]}}",
"redhat_vex": {
"aggregate_severity": "Moderate",
"current_release_date": "2026-09-02T19:03:37+00:00",
"cve": "CVE-2026-84377",
"id": "CVE-2026-84377",
"initial_release_date": "2026-09-02T17:18:32.728000+00:00",
"product_status:known_affected": "9",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "litellm: LiteLLM: Authenticated Server-Side Request Forgery and credential exposure",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-84377.json",
"version": "3"
},
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-84377\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-09-03T14:06:05.318151Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-09-03T14:05:23.437Z\"}}], \"cna\": {\"title\": \"LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters\", \"source\": {\"advisory\": \"GHSA-3cv6-jpf6-8222\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 6.5, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"BerriAI\", \"product\": \"litellm\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.88.6\"}, {\"status\": \"affected\", \"version\": \"\u003e= 1.89.0, \u003c 1.96.2\"}]}], \"references\": [{\"url\": \"https://github.com/BerriAI/litellm/security/advisories/GHSA-3cv6-jpf6-8222\", \"name\": \"https://github.com/BerriAI/litellm/security/advisories/GHSA-3cv6-jpf6-8222\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/BerriAI/litellm/pull/36011\", \"name\": \"https://github.com/BerriAI/litellm/pull/36011\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/BerriAI/litellm/pull/36314\", \"name\": \"https://github.com/BerriAI/litellm/pull/36314\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/BerriAI/litellm/pull/36494\", \"name\": \"https://github.com/BerriAI/litellm/pull/36494\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/BerriAI/litellm/commit/473f72e63a9777d793fbbf57194d8ec4fb97bc1b\", \"name\": \"https://github.com/BerriAI/litellm/commit/473f72e63a9777d793fbbf57194d8ec4fb97bc1b\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/BerriAI/litellm/commit/820f247a6abba55cd87d130bef7bba7be3b29d37\", \"name\": \"https://github.com/BerriAI/litellm/commit/820f247a6abba55cd87d130bef7bba7be3b29d37\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/BerriAI/litellm/commit/c898d341c02299cf2506d0d8e84cc67953043593\", \"name\": \"https://github.com/BerriAI/litellm/commit/c898d341c02299cf2506d0d8e84cc67953043593\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/BerriAI/litellm/releases/tag/v1.88.6\", \"name\": \"https://github.com/BerriAI/litellm/releases/tag/v1.88.6\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/BerriAI/litellm/releases/tag/v1.96.2\", \"name\": \"https://github.com/BerriAI/litellm/releases/tag/v1.96.2\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials to that destination. Request validation in litellm/proxy/auth/auth_utils.py, litellm/proxy/common_request_processing.py, litellm/proxy/health_endpoints/_health_endpoints.py, litellm/proxy/image_endpoints/endpoints.py, and litellm/proxy/litellm_pre_call_utils.py used incomplete checks that did not cover every sensitive parameter or inspect equivalent values across nested request fields, path values, and bracket-notation form data. Routing and credential parameters including api_base, base_url, model_list, fallbacks, and litellm_credential_name could therefore be applied without clearing the operator\u0027s stored key, exposing upstream provider credentials and other configured secrets and permitting server-side requests to internal services reachable by the proxy. This issue is fixed in versions 1.88.6 and 1.96.2.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-918\", \"description\": \"CWE-918: Server-Side Request Forgery (SSRF)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-09-02T17:18:32.728Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-84377\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-09-03T14:31:30.548Z\", \"dateReserved\": \"2026-09-01T16:27:58.129Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-09-02T17:18:32.728Z\", \"assignerShortName\": \"GitHub_M\"}",
"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.
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.
Loading…
Loading…