CVE-2024-2952 (GCVE-0-2024-2952)

Vulnerability from cvelistv5 – Published: 2024-04-10 17:07 – Updated: 2024-08-01 19:32
VLAI?
Summary
BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.
Severity ?
9.8 (Critical)
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CWE
  • CWE-76 - Improper Neutralization of Equivalent Special Elements
Assigner
References
Impacted products
Vendor Product Version
berriai berriai/litellm Affected: unspecified , < 1.34.42 (custom)
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "affected": [
          {
            "cpes": [
              "cpe:2.3:a:berriai:litellm:*:*:*:*:*:*:*:*"
            ],
            "defaultStatus": "unknown",
            "product": "litellm",
            "vendor": "berriai",
            "versions": [
              {
                "lessThan": "1.34.42",
                "status": "affected",
                "version": "1.23.2",
                "versionType": "custom"
              }
            ]
          }
        ],
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2024-2952",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-07-03T15:32:17.112100Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2024-07-03T16:51:12.428Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      },
      {
        "providerMetadata": {
          "dateUpdated": "2024-08-01T19:32:42.587Z",
          "orgId": "af854a3a-2127-422b-91ae-364da2661108",
          "shortName": "CVE"
        },
        "references": [
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4"
          },
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3"
          }
        ],
        "title": "CVE Program Container"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "berriai/litellm",
          "vendor": "berriai",
          "versions": [
            {
              "lessThan": "1.34.42",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server."
        }
      ],
      "metrics": [
        {
          "cvssV3_0": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.8,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.0"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-76",
              "description": "CWE-76 Improper Neutralization of Equivalent Special Elements",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2024-04-16T11:10:21.535Z",
        "orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
        "shortName": "@huntr_ai"
      },
      "references": [
        {
          "url": "https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4"
        },
        {
          "url": "https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3"
        }
      ],
      "source": {
        "advisory": "a9e0a164-6de0-43a4-a640-0cbfb54220a4",
        "discovery": "EXTERNAL"
      },
      "title": "Server-Side Template Injection in BerriAI/litellm"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
    "assignerShortName": "@huntr_ai",
    "cveId": "CVE-2024-2952",
    "datePublished": "2024-04-10T17:07:52.935Z",
    "dateReserved": "2024-03-26T18:00:46.844Z",
    "dateUpdated": "2024-08-01T19:32:42.587Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "fkie_nvd": {
      "descriptions": "[{\"lang\": \"en\", \"value\": \"BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.\"}, {\"lang\": \"es\", \"value\": \"BerriAI/litellm es vulnerable a Server-Side Template Injection (SSTI) a trav\\u00e9s del endpoint `/completions`. La vulnerabilidad surge del m\\u00e9todo `hf_chat_template` que procesa el par\\u00e1metro `chat_template` del archivo `tokenizer_config.json` a trav\\u00e9s del motor de plantillas Jinja sin una sanitizaci\\u00f3n adecuada. Los atacantes pueden aprovechar esto creando archivos maliciosos `tokenizer_config.json` que ejecutan c\\u00f3digo arbitrario en el servidor.\"}]",
      "id": "CVE-2024-2952",
      "lastModified": "2024-11-21T09:10:55.170",
      "metrics": "{\"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:H/A:H\", \"baseScore\": 9.8, \"baseSeverity\": \"CRITICAL\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"HIGH\", \"integrityImpact\": \"HIGH\", \"availabilityImpact\": \"HIGH\"}, \"exploitabilityScore\": 3.9, \"impactScore\": 5.9}]}",
      "published": "2024-04-10T17:15:54.823",
      "references": "[{\"url\": \"https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3\", \"source\": \"security@huntr.dev\"}, {\"url\": \"https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4\", \"source\": \"security@huntr.dev\"}, {\"url\": \"https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\"}, {\"url\": \"https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\"}]",
      "sourceIdentifier": "security@huntr.dev",
      "vulnStatus": "Awaiting Analysis",
      "weaknesses": "[{\"source\": \"security@huntr.dev\", \"type\": \"Secondary\", \"description\": [{\"lang\": \"en\", \"value\": \"CWE-76\"}]}]"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2024-2952\",\"sourceIdentifier\":\"security@huntr.dev\",\"published\":\"2024-04-10T17:15:54.823\",\"lastModified\":\"2025-07-15T14:21:14.340\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.\"},{\"lang\":\"es\",\"value\":\"BerriAI/litellm es vulnerable a Server-Side Template Injection (SSTI) a trav\u00e9s del endpoint `/completions`. La vulnerabilidad surge del m\u00e9todo `hf_chat_template` que procesa el par\u00e1metro `chat_template` del archivo `tokenizer_config.json` a trav\u00e9s del motor de plantillas Jinja sin una sanitizaci\u00f3n adecuada. Los atacantes pueden aprovechar esto creando archivos maliciosos `tokenizer_config.json` que ejecutan c\u00f3digo arbitrario en el servidor.\"}],\"metrics\":{\"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:H/A:H\",\"baseScore\":9.8,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":5.9}]},\"weaknesses\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-76\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"1.34.42\",\"matchCriteriaId\":\"4720F198-5C9D-477B-B77A-A05859CA50BC\"}]}]}],\"references\":[{\"url\":\"https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3\",\"source\":\"security@huntr.dev\",\"tags\":[\"Patch\"]},{\"url\":\"https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4\",\"source\":\"security@huntr.dev\",\"tags\":[\"Exploit\",\"Third Party Advisory\"]},{\"url\":\"https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Patch\"]},{\"url\":\"https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\",\"tags\":[\"Exploit\",\"Third Party Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CVE Program Container\", \"references\": [{\"url\": \"https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4\", \"tags\": [\"x_transferred\"]}, {\"url\": \"https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3\", \"tags\": [\"x_transferred\"]}], \"providerMetadata\": {\"orgId\": \"af854a3a-2127-422b-91ae-364da2661108\", \"shortName\": \"CVE\", \"dateUpdated\": \"2024-08-01T19:32:42.587Z\"}}, {\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2024-2952\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2024-07-03T15:32:17.112100Z\"}}}], \"affected\": [{\"cpes\": [\"cpe:2.3:a:berriai:litellm:*:*:*:*:*:*:*:*\"], \"vendor\": \"berriai\", \"product\": \"litellm\", \"versions\": [{\"status\": \"affected\", \"version\": \"1.23.2\", \"lessThan\": \"1.34.42\", \"versionType\": \"custom\"}], \"defaultStatus\": \"unknown\"}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2024-07-03T16:49:17.615Z\"}}], \"cna\": {\"title\": \"Server-Side Template Injection in BerriAI/litellm\", \"source\": {\"advisory\": \"a9e0a164-6de0-43a4-a640-0cbfb54220a4\", \"discovery\": \"EXTERNAL\"}, \"metrics\": [{\"cvssV3_0\": {\"scope\": \"UNCHANGED\", \"version\": \"3.0\", \"baseScore\": 9.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"berriai\", \"product\": \"berriai/litellm\", \"versions\": [{\"status\": \"affected\", \"version\": \"unspecified\", \"lessThan\": \"1.34.42\", \"versionType\": \"custom\"}]}], \"references\": [{\"url\": \"https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4\"}, {\"url\": \"https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3\"}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-76\", \"description\": \"CWE-76 Improper Neutralization of Equivalent Special Elements\"}]}], \"providerMetadata\": {\"orgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"shortName\": \"@huntr_ai\", \"dateUpdated\": \"2024-04-16T11:10:21.535Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2024-2952\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2024-08-01T19:32:42.587Z\", \"dateReserved\": \"2024-03-26T18:00:46.844Z\", \"assignerOrgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"datePublished\": \"2024-04-10T17:07:52.935Z\", \"assignerShortName\": \"@huntr_ai\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.1"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

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.