GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

FKIE_CVE-2024-2952

Vulnerability from fkie_nvd - Published: 2024-04-10 17:15 - Updated: 2026-06-17 07:25
Severity
9.8 (Critical) - CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
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.
References
security@huntr.devhttps://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3Patch
security@huntr.devhttps://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4Exploit, Third Party Advisory
af854a3a-2127-422b-91ae-364da2661108https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3Patch
af854a3a-2127-422b-91ae-364da2661108https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4Exploit, Third Party Advisory
Impacted products
Vendor Product Version
litellm litellm *
To clipboard 

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "berriai/litellm",
          "vendor": "berriai",
          "versions": [
            {
              "lessThan": "1.34.42",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "source": "security@huntr.dev"
    },
    {
      "affectedData": [
        {
          "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"
            }
          ]
        }
      ],
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "4720F198-5C9D-477B-B77A-A05859CA50BC",
              "versionEndExcluding": "1.34.42",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "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."
    }
  ],
  "id": "CVE-2024-2952",
  "lastModified": "2026-06-17T07:25:53.840",
  "metrics": {
    "cvssMetricV30": [
      {
        "cvssData": {
          "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"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 5.9,
        "source": "security@huntr.dev",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2024-2952",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2024-07-03T15:32:17.112100Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2024-04-10T17:15:54.823",
  "references": [
    {
      "source": "security@huntr.dev",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3"
    },
    {
      "source": "security@huntr.dev",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4"
    },
    {
      "source": "af854a3a-2127-422b-91ae-364da2661108",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/berriai/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3"
    },
    {
      "source": "af854a3a-2127-422b-91ae-364da2661108",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4"
    }
  ],
  "sourceIdentifier": "security@huntr.dev",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-76"
        }
      ],
      "source": "security@huntr.dev",
      "type": "Secondary"
    }
  ]
}



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.


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.