CVE-2026-89032 (GCVE-0-2026-89032)
Vulnerability from cvelistv5 – Published: 2026-09-25 16:04 – Updated: 2026-10-01 15:21 X_Open Source
VLAI
EPSS
VEX
Title
BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer
Summary
BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants' personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-30 00:00 UTC
CWE
- CWE-863 - Incorrect Authorization
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/BerriAI/litellm/releases/tag/v… | release-notes |
| https://github.com/BerriAI/litellm/pull/39590 | issue-trackingpatch |
| https://github.com/BerriAI/litellm/commit/16db51e… | patch |
| https://www.vulncheck.com/advisories/berriai-lite… | third-party-advisory |
Impacted products
Date Public
2026-09-03 00:00
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-89032",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-30T00:00:00+00:00",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-10-01T03:55:46.572Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:github/BerriAI/litellm",
"product": "litellm",
"repo": "https://github.com/BerriAI/litellm",
"vendor": "BerriAI",
"versions": [
{
"lessThan": "1.101.0-rc.1",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*",
"versionEndExcluding": "1.101.0-rc.1",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Tanguy Snoeck"
}
],
"datePublic": "2026-09-03T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants\u0027 cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants\u0027 personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "HIGH",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.7,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "HIGH",
"userInteraction": "PASSIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:P/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.7,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "Incorrect Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-01T15:21:54.281Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "LiteLLM v1.101.0-rc.1 Release Notes",
"tags": [
"release-notes"
],
"url": "https://github.com/BerriAI/litellm/releases/tag/v1.101.0-rc.1"
},
{
"name": "Pull Request",
"tags": [
"issue-tracking",
"patch"
],
"url": "https://github.com/BerriAI/litellm/pull/39590"
},
{
"name": "Patch Commit",
"tags": [
"patch"
],
"url": "https://github.com/BerriAI/litellm/commit/16db51e2cfc28e02bd460481e634a8403ea9265e"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/berriai-litellm-rc-1-tenant-isolation-bypass-via-semantic-cache-layer"
}
],
"source": {
"discovery": "UNKNOWN"
},
"tags": [
"x_open-source"
],
"title": "BerriAI LiteLLM \u003c 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-89032",
"datePublished": "2026-09-25T16:04:47.964Z",
"dateReserved": "2026-09-10T16:23:54.472Z",
"dateUpdated": "2026-10-01T15:21:54.281Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-89032",
"date": "2026-10-19",
"epss": "0.00272",
"percentile": "0.18381"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:github/BerriAI/litellm",
"product": "litellm",
"repo": "https://github.com/BerriAI/litellm",
"vendor": "BerriAI",
"versions": [
{
"lessThan": "1.101.0-rc.1",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"source": "disclosure@vulncheck.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants\u0027 cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants\u0027 personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal."
}
],
"id": "CVE-2026-89032",
"lastModified": "2026-10-01T04:18:21.403",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.7,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:N",
"version": "3.1"
},
"exploitabilityScore": 1.3,
"impactScore": 5.8,
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "HIGH",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 8.7,
"baseSeverity": "HIGH",
"confidentialityRequirement": "NOT_DEFINED",
"exploitMaturity": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "HIGH",
"userInteraction": "PASSIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:P/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-89032",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-30T00:00:00+00:00",
"version": "2.0.3"
}
}
]
},
"published": "2026-09-25T17:17:18.793",
"references": [
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/BerriAI/litellm/commit/16db51e2cfc28e02bd460481e634a8403ea9265e"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/BerriAI/litellm/pull/39590"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/BerriAI/litellm/releases/tag/v1.101.0-rc.1"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://www.vulncheck.com/advisories/berriai-litellm-rc-1-tenant-isolation-bypass-via-semantic-cache-layer"
}
],
"sourceIdentifier": "disclosure@vulncheck.com",
"vulnStatus": "Awaiting Analysis",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-863"
}
],
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"aggregate_severity": "Important",
"current_release_date": "2026-10-19T11:30:24+00:00",
"cve": "CVE-2026-89032",
"id": "CVE-2026-89032",
"initial_release_date": "2026-09-25T16:04:47.964000+00:00",
"product_status:fixed": "4",
"product_status:known_affected": "8",
"product_status:known_not_affected": "317",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "litellm: LiteLLM: Information disclosure via semantic cache metadata mismatch",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-89032.json",
"version": "3"
},
"suse_vex": {
"aggregate_severity": "important",
"current_release_date": "2026-10-01T00:42:48Z",
"cve": "CVE-2026-89032",
"id": "CVE-2026-89032",
"initial_release_date": "2026-09-26T16:22:30Z",
"product_status:recommended": "1",
"source": "SUSE CSAF VEX",
"status": "interim",
"title": "SUSE CVE CVE-2026-89032",
"url": "https://ftp.suse.com/pub/projects/security/csaf-vex/cve-2026-89032.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-89032",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-30T15:45:14.938477Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-30T17:25:35.345Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:github/BerriAI/litellm",
"product": "litellm",
"repo": "https://github.com/BerriAI/litellm",
"vendor": "BerriAI",
"versions": [
{
"lessThan": "1.101.0-rc.1",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*",
"versionEndExcluding": "1.101.0-rc.1",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Tanguy Snoeck"
}
],
"datePublic": "2026-09-03T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants\u0027 cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants\u0027 personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "HIGH",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.7,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "HIGH",
"userInteraction": "PASSIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:P/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
},
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.7,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "Incorrect Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-01T15:21:54.281Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "LiteLLM v1.101.0-rc.1 Release Notes",
"tags": [
"release-notes"
],
"url": "https://github.com/BerriAI/litellm/releases/tag/v1.101.0-rc.1"
},
{
"name": "Pull Request",
"tags": [
"issue-tracking",
"patch"
],
"url": "https://github.com/BerriAI/litellm/pull/39590"
},
{
"name": "Patch Commit",
"tags": [
"patch"
],
"url": "https://github.com/BerriAI/litellm/commit/16db51e2cfc28e02bd460481e634a8403ea9265e"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/berriai-litellm-rc-1-tenant-isolation-bypass-via-semantic-cache-layer"
}
],
"source": {
"discovery": "UNKNOWN"
},
"tags": [
"x_open-source"
],
"title": "BerriAI LiteLLM \u003c 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer",
"x_generator": {
"engine": "vulncheck"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-89032",
"datePublished": "2026-09-25T16:04:47.964Z",
"dateReserved": "2026-09-10T16:23:54.472Z",
"dateUpdated": "2026-10-01T15:21:54.281Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
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.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
Loading timeline…
Loading…
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.