CVE-2024-6587 (GCVE-0-2024-6587)
Vulnerability from cvelistv5 – Published: 2024-09-13 15:59 – Updated: 2024-09-13 16:53Title
SSRF in berriai/litellm
Summary
A Server-Side Request Forgery (SSRF) vulnerability exists in berriai/litellm version 1.38.10. This vulnerability allows users to specify the `api_base` parameter when making requests to `POST /chat/completions`, causing the application to send the request to the domain specified by `api_base`. This request includes the OpenAI API key. A malicious user can set the `api_base` to their own domain and intercept the OpenAI API key, leading to unauthorized access and potential misuse of the API key.
Severity
7.5 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2024-09-13 16:52 UTC
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
Impacted products
2 products
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| berriai | berriai/litellm |
Affected:
unspecified , < 1.44.9
(custom)
|
guessed | |
| berriai | litellm |
Affected:
0 , < 1.44.9
(custom)
cpe:2.3:a:berriai:litellm:*:*:*:*:*:*:*:* |
Shadowserver
Known Exploited Vulnerability - GCVE BCP-07 Compliant
KEV entry ID: ce3bfd59-5fcb-4339-a375-dc93f3ba1223
Exploited: Yes
Characteristics
Severity:
75.0
Timestamps
First Seen: 2024-08-22
Asserted: 2024-08-22
Last Seen: 2026-07-16
Scope
Asset Exposure: ['internet-facing']
Notes: Affected: LiteLLM / LiteLLM | Class: other-software | Severity: High (CVSS 7.5) | IoT: no | In CISA KEV: no | Honeypot connections on 2026-07-16: 8
Evidence
Type: Honeypot
Signal: In The Wild Attempts
Confidence: 70%
Source: shadowserver
Details
| 1D | 1 |
|---|---|
| Iot | no |
| Feed | Shadowserver Foundation honeypot/exploited-vulnerabilities |
| Type | http-scan |
| Class | other-software |
| 7D Avg | 0 |
| Vendor | LiteLLM |
| 30D Avg | 0 |
| 90D Avg | 2 |
| Product | LiteLLM |
| Cisa Kev | no |
| Connections | 8 |
| Observation Date | 2026-07-16 |
| Vulnerability Class | CVSS |
| Vulnerability Score | 7.5 |
| Vulnerability Severity | High |
References
Created: 2026-06-30 09:23 UTC
| Updated: 2026-07-18 01:02 UTC
Previdian
Known Exploited Vulnerability - GCVE BCP-07 Compliant
KEV entry ID: 58fd9c3c-4ecb-462d-a946-7f6a7de446e9
Exploited: Yes
Timestamps
First Seen: 2024-09-13
Asserted: 2024-09-13
Scope
Notes: KEVIntel entry: SSRF in berriai/litellm | Affected: berriai / berriai/litellm | CVSS: 7.5 (HIGH) | Used in malware: unknown | Not yet in CISA KEV: True
Evidence
Type: Public Report
Signal: Successful Exploitation
Confidence: 70%
Source: kevintel
Details
| Feed | KEVIntel (kevintel.com) |
|---|---|
| Title | SSRF in berriai/litellm |
| Vendor | berriai |
| Product | berriai/litellm |
| Added Date | 2024-09-13T15:59:53.000Z |
| Cvss Score | 7.5 |
| Epss Score | None |
| Cvss Severity | HIGH |
| Epss Percentile | None |
| Used In Malware | unknown |
| Ahead Of Cisa Kev | None |
| Not Yet In Cisa Kev | True |
References
Created: 2026-06-23 14:06 UTC
| Updated: 2026-07-10 06:14 UTC
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:berriai:litellm:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "litellm",
"vendor": "berriai",
"versions": [
{
"lessThan": "1.44.9",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-6587",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-09-13T16:52:13.638830Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-09-13T16:53:11.849Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "berriai/litellm",
"vendor": "berriai",
"versions": [
{
"lessThan": "1.44.9",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A Server-Side Request Forgery (SSRF) vulnerability exists in berriai/litellm version 1.38.10. This vulnerability allows users to specify the `api_base` parameter when making requests to `POST /chat/completions`, causing the application to send the request to the domain specified by `api_base`. This request includes the OpenAI API key. A malicious user can set the `api_base` to their own domain and intercept the OpenAI API key, leading to unauthorized access and potential misuse of the API key."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918 Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-09-13T15:59:53.557Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/4001e1a2-7b7a-4776-a3ae-e6692ec3d997"
},
{
"url": "https://github.com/berriai/litellm/commit/ba1912afd1b19e38d3704bb156adf887f91ae1e0"
}
],
"source": {
"advisory": "4001e1a2-7b7a-4776-a3ae-e6692ec3d997",
"discovery": "EXTERNAL"
},
"title": "SSRF in berriai/litellm"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-6587",
"datePublished": "2024-09-13T15:59:53.557Z",
"dateReserved": "2024-07-08T21:33:48.001Z",
"dateUpdated": "2024-09-13T16:53:11.849Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2024-6587",
"date": "2026-09-16",
"epss": "0.35316",
"percentile": "0.98362"
},
"fkie_nvd": {
"configurations": "[{\"nodes\": [{\"operator\": \"OR\", \"negate\": false, \"cpeMatch\": [{\"vulnerable\": true, \"criteria\": \"cpe:2.3:a:litellm:litellm:1.38.10:*:*:*:*:*:*:*\", \"matchCriteriaId\": \"E7A51391-C50E-4D40-AAFD-1185132EF575\"}]}]}]",
"descriptions": "[{\"lang\": \"en\", \"value\": \"A Server-Side Request Forgery (SSRF) vulnerability exists in berriai/litellm version 1.38.10. This vulnerability allows users to specify the `api_base` parameter when making requests to `POST /chat/completions`, causing the application to send the request to the domain specified by `api_base`. This request includes the OpenAI API key. A malicious user can set the `api_base` to their own domain and intercept the OpenAI API key, leading to unauthorized access and potential misuse of the API key.\"}, {\"lang\": \"es\", \"value\": \"Existe una vulnerabilidad de Server-Side Request Forgery (SSRF) en la versi\\u00f3n 1.38.10 de berriai/litellm. Esta vulnerabilidad permite a los usuarios especificar el par\\u00e1metro `api_base` al realizar solicitudes a `POST /chat/completions`, lo que hace que la aplicaci\\u00f3n env\\u00ede la solicitud al dominio especificado por `api_base`. Esta solicitud incluye la clave API de OpenAI. Un usuario malintencionado puede configurar `api_base` en su propio dominio e interceptar la clave API de OpenAI, lo que provoca un acceso no autorizado y un posible uso indebido de la clave API.\"}]",
"id": "CVE-2024-6587",
"lastModified": "2024-09-20T14:55:16.423",
"metrics": "{\"cvssMetricV31\": [{\"source\": \"nvd@nist.gov\", \"type\": \"Primary\", \"cvssData\": {\"version\": \"3.1\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N\", \"baseScore\": 7.5, \"baseSeverity\": \"HIGH\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"HIGH\", \"integrityImpact\": \"NONE\", \"availabilityImpact\": \"NONE\"}, \"exploitabilityScore\": 3.9, \"impactScore\": 3.6}], \"cvssMetricV30\": [{\"source\": \"security@huntr.dev\", \"type\": \"Secondary\", \"cvssData\": {\"version\": \"3.0\", \"vectorString\": \"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N\", \"baseScore\": 7.5, \"baseSeverity\": \"HIGH\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"HIGH\", \"integrityImpact\": \"NONE\", \"availabilityImpact\": \"NONE\"}, \"exploitabilityScore\": 3.9, \"impactScore\": 3.6}]}",
"published": "2024-09-13T16:15:04.637",
"references": "[{\"url\": \"https://github.com/berriai/litellm/commit/ba1912afd1b19e38d3704bb156adf887f91ae1e0\", \"source\": \"security@huntr.dev\", \"tags\": [\"Patch\"]}, {\"url\": \"https://huntr.com/bounties/4001e1a2-7b7a-4776-a3ae-e6692ec3d997\", \"source\": \"security@huntr.dev\", \"tags\": [\"Exploit\", \"Third Party Advisory\"]}]",
"sourceIdentifier": "security@huntr.dev",
"vulnStatus": "Analyzed",
"weaknesses": "[{\"source\": \"security@huntr.dev\", \"type\": \"Primary\", \"description\": [{\"lang\": \"en\", \"value\": \"CWE-918\"}]}]"
},
"nvd": "{\"cve\":{\"id\":\"CVE-2024-6587\",\"sourceIdentifier\":\"security@huntr.dev\",\"published\":\"2024-09-13T16:15:04.637\",\"lastModified\":\"2026-06-17T08:18:17.787\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"A Server-Side Request Forgery (SSRF) vulnerability exists in berriai/litellm version 1.38.10. This vulnerability allows users to specify the `api_base` parameter when making requests to `POST /chat/completions`, causing the application to send the request to the domain specified by `api_base`. This request includes the OpenAI API key. A malicious user can set the `api_base` to their own domain and intercept the OpenAI API key, leading to unauthorized access and potential misuse of the API key.\"},{\"lang\":\"es\",\"value\":\"Existe una vulnerabilidad de Server-Side Request Forgery (SSRF) en la versi\u00f3n 1.38.10 de berriai/litellm. Esta vulnerabilidad permite a los usuarios especificar el par\u00e1metro `api_base` al realizar solicitudes a `POST /chat/completions`, lo que hace que la aplicaci\u00f3n env\u00ede la solicitud al dominio especificado por `api_base`. Esta solicitud incluye la clave API de OpenAI. Un usuario malintencionado puede configurar `api_base` en su propio dominio e interceptar la clave API de OpenAI, lo que provoca un acceso no autorizado y un posible uso indebido de la clave API.\"}],\"affected\":[{\"source\":\"security@huntr.dev\",\"affectedData\":[{\"vendor\":\"berriai\",\"product\":\"berriai/litellm\",\"versions\":[{\"version\":\"unspecified\",\"lessThan\":\"1.44.9\",\"versionType\":\"custom\",\"status\":\"affected\"}]}]},{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"affectedData\":[{\"vendor\":\"berriai\",\"product\":\"litellm\",\"defaultStatus\":\"unknown\",\"cpes\":[\"cpe:2.3:a:berriai:litellm:*:*:*:*:*:*:*:*\"],\"versions\":[{\"version\":\"0\",\"lessThan\":\"1.44.9\",\"versionType\":\"custom\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N\",\"baseScore\":7.5,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":3.9,\"impactScore\":3.6}],\"cvssMetricV30\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.0\",\"vectorString\":\"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N\",\"baseScore\":7.5,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":3.9,\"impactScore\":3.6}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2024-09-13T16:52:13.638830Z\",\"id\":\"CVE-2024-6587\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"partial\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:litellm:litellm:1.38.10:*:*:*:*:*:*:*\",\"matchCriteriaId\":\"E7A51391-C50E-4D40-AAFD-1185132EF575\"}]}]}],\"references\":[{\"url\":\"https://github.com/berriai/litellm/commit/ba1912afd1b19e38d3704bb156adf887f91ae1e0\",\"source\":\"security@huntr.dev\",\"tags\":[\"Patch\"]},{\"url\":\"https://huntr.com/bounties/4001e1a2-7b7a-4776-a3ae-e6692ec3d997\",\"source\":\"security@huntr.dev\",\"tags\":[\"Exploit\",\"Third Party Advisory\"]}]}}",
"redhat_vex": {
"current_release_date": "2025-05-28T19:20:33+00:00",
"cve": "CVE-2024-6587",
"id": "CVE-2024-6587",
"initial_release_date": "2024-01-01T00:00:00+00:00",
"product_status:known_not_affected": "1",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "SSRF in berriai/litellm",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2024/cve-2024-6587.json",
"version": "3"
},
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2024-6587\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2024-09-13T16:52:13.638830Z\"}}}], \"affected\": [{\"cpes\": [\"cpe:2.3:a:berriai:litellm:*:*:*:*:*:*:*:*\"], \"vendor\": \"berriai\", \"product\": \"litellm\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"lessThan\": \"1.44.9\", \"versionType\": \"custom\"}], \"defaultStatus\": \"unknown\"}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2024-09-13T16:53:02.619Z\"}}], \"cna\": {\"title\": \"SSRF in berriai/litellm\", \"source\": {\"advisory\": \"4001e1a2-7b7a-4776-a3ae-e6692ec3d997\", \"discovery\": \"EXTERNAL\"}, \"metrics\": [{\"cvssV3_0\": {\"scope\": \"UNCHANGED\", \"version\": \"3.0\", \"baseScore\": 7.5, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"berriai\", \"product\": \"berriai/litellm\", \"versions\": [{\"status\": \"affected\", \"version\": \"unspecified\", \"lessThan\": \"1.44.9\", \"versionType\": \"custom\"}]}], \"references\": [{\"url\": \"https://huntr.com/bounties/4001e1a2-7b7a-4776-a3ae-e6692ec3d997\"}, {\"url\": \"https://github.com/berriai/litellm/commit/ba1912afd1b19e38d3704bb156adf887f91ae1e0\"}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"A Server-Side Request Forgery (SSRF) vulnerability exists in berriai/litellm version 1.38.10. This vulnerability allows users to specify the `api_base` parameter when making requests to `POST /chat/completions`, causing the application to send the request to the domain specified by `api_base`. This request includes the OpenAI API key. A malicious user can set the `api_base` to their own domain and intercept the OpenAI API key, leading to unauthorized access and potential misuse of the API key.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-918\", \"description\": \"CWE-918 Server-Side Request Forgery (SSRF)\"}]}], \"providerMetadata\": {\"orgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"shortName\": \"@huntr_ai\", \"dateUpdated\": \"2024-09-13T15:59:53.557Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2024-6587\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2024-09-13T16:53:11.849Z\", \"dateReserved\": \"2024-07-08T21:33:48.001Z\", \"assignerOrgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"datePublished\": \"2024-09-13T15:59:53.557Z\", \"assignerShortName\": \"@huntr_ai\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
}
}
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…