CVE-2026-42203 (GCVE-0-2026-42203)

Vulnerability from cvelistv5 – Published: 2026-05-08 03:36 – Updated: 2026-05-08 14:36
VLAI?
Title
LiteLLM: Server-Side Template Injection in /prompts/test endpoint
Summary
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.
Severity ?
8.6 (High)
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N
CWE
  • CWE-1336 - Improper Neutralization of Special Elements Used in a Template Engine
Assigner
References
Impacted products
Vendor Product Version
BerriAI litellm Affected: >= 1.80.5, < 1.83.7
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-42203",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-08T14:36:50.142914Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-08T14:36:57.479Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "litellm",
          "vendor": "BerriAI",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 1.80.5, \u003c 1.83.7"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 8.6,
            "baseSeverity": "HIGH",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1336",
              "description": "CWE-1336: Improper Neutralization of Special Elements Used in a Template Engine",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-08T03:36:58.648Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862"
        },
        {
          "name": "https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable"
        }
      ],
      "source": {
        "advisory": "GHSA-xqmj-j6mv-4862",
        "discovery": "UNKNOWN"
      },
      "title": "LiteLLM: Server-Side Template Injection in /prompts/test endpoint"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-42203",
    "datePublished": "2026-05-08T03:36:58.648Z",
    "dateReserved": "2026-04-25T05:04:37.027Z",
    "dateUpdated": "2026-05-08T14:36:57.479Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-42203",
      "date": "2026-05-08",
      "epss": "0.00047",
      "percentile": "0.14308"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-42203\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-08T04:16:19.450\",\"lastModified\":\"2026-05-08T15:52:24.790\",\"vulnStatus\":\"Undergoing Analysis\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.\"}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/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\",\"baseScore\":8.6,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"attackRequirements\":\"NONE\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"vulnConfidentialityImpact\":\"HIGH\",\"vulnIntegrityImpact\":\"HIGH\",\"vulnAvailabilityImpact\":\"NONE\",\"subConfidentialityImpact\":\"NONE\",\"subIntegrityImpact\":\"NONE\",\"subAvailabilityImpact\":\"NONE\",\"exploitMaturity\":\"NOT_DEFINED\",\"confidentialityRequirement\":\"NOT_DEFINED\",\"integrityRequirement\":\"NOT_DEFINED\",\"availabilityRequirement\":\"NOT_DEFINED\",\"modifiedAttackVector\":\"NOT_DEFINED\",\"modifiedAttackComplexity\":\"NOT_DEFINED\",\"modifiedAttackRequirements\":\"NOT_DEFINED\",\"modifiedPrivilegesRequired\":\"NOT_DEFINED\",\"modifiedUserInteraction\":\"NOT_DEFINED\",\"modifiedVulnConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedVulnIntegrityImpact\":\"NOT_DEFINED\",\"modifiedVulnAvailabilityImpact\":\"NOT_DEFINED\",\"modifiedSubConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedSubIntegrityImpact\":\"NOT_DEFINED\",\"modifiedSubAvailabilityImpact\":\"NOT_DEFINED\",\"Safety\":\"NOT_DEFINED\",\"Automatable\":\"NOT_DEFINED\",\"Recovery\":\"NOT_DEFINED\",\"valueDensity\":\"NOT_DEFINED\",\"vulnerabilityResponseEffort\":\"NOT_DEFINED\",\"providerUrgency\":\"NOT_DEFINED\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-1336\"}]}],\"references\":[{\"url\":\"https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862\",\"source\":\"security-advisories@github.com\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-42203\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-08T14:36:50.142914Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-08T14:36:54.287Z\"}}], \"cna\": {\"title\": \"LiteLLM: Server-Side Template Injection in /prompts/test endpoint\", \"source\": {\"advisory\": \"GHSA-xqmj-j6mv-4862\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV4_0\": {\"version\": \"4.0\", \"baseScore\": 8.6, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"NONE\", \"privilegesRequired\": \"LOW\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"NONE\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"BerriAI\", \"product\": \"litellm\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 1.80.5, \u003c 1.83.7\"}]}], \"references\": [{\"url\": \"https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862\", \"name\": \"https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable\", \"name\": \"https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-1336\", \"description\": \"CWE-1336: Improper Neutralization of Special Elements Used in a Template Engine\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-08T03:36:58.648Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-42203\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-05-08T14:36:57.479Z\", \"dateReserved\": \"2026-04-25T05:04:37.027Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-08T03:36:58.648Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




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.



Detection rules are retrieved from Rulezet.