GHSA-3CV6-JPF6-8222

Vulnerability from github – Published: 2026-09-30 21:11 – Updated: 2026-09-30 21:11
VLAI
Summary
LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters
Details

Impact

Any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination they control and cause the proxy to send its own configured provider credentials to that destination. The proxy's request-body validation was a denylist that did not cover every sensitive parameter and did not inspect parameters nested inside other request fields, so a caller could supply a routing or credential value that the proxy applied without clearing the operator's stored key. Any authenticated user could therefore exfiltrate the operator's upstream provider credentials and other configured secrets, and perform Server-Side Request Forgery against internal services reachable from the proxy.

Patches

Fixed in 1.96.2, 1.95.1, 1.94.3, 1.93.2, 1.92.2, 1.91.5, 1.90.7, 1.89.7, and 1.88.6.

Workarounds

Set general_settings.allow_client_side_credentials to false so callers cannot override connection parameters, restrict proxy keys to trusted callers, and block the affected parameters (api_base, base_url, model_list, fallbacks, provider credential fields) at a reverse proxy or API gateway.

Severity
6.5 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.88.6"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.89.0"
            },
            {
              "fixed": "1.89.7"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.90.0"
            },
            {
              "fixed": "1.90.7"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.91.0"
            },
            {
              "fixed": "1.91.5"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.92.0"
            },
            {
              "fixed": "1.92.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.93.0"
            },
            {
              "fixed": "1.93.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.94.0"
            },
            {
              "fixed": "1.94.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.95.0"
            },
            {
              "fixed": "1.95.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.96.0"
            },
            {
              "fixed": "1.96.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-84377"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-09-30T21:11:25Z",
    "nvd_published_at": "2026-09-02T18:21:28Z",
    "severity": "MODERATE"
  },
  "details": "### Impact\n\nAny authenticated LiteLLM proxy user could redirect an outbound provider call to a destination they control and cause the proxy to send its own configured provider credentials to that destination. The proxy\u0027s request-body validation was a denylist that did not cover every sensitive parameter and did not inspect parameters nested inside other request fields, so a caller could supply a routing or credential value that the proxy applied without clearing the operator\u0027s stored key. Any authenticated user could therefore exfiltrate the operator\u0027s upstream provider credentials and other configured secrets, and perform Server-Side Request Forgery against internal services reachable from the proxy.\n\n### Patches\n\nFixed in 1.96.2, 1.95.1, 1.94.3, 1.93.2, 1.92.2, 1.91.5, 1.90.7, 1.89.7, and 1.88.6.\n\n### Workarounds\n\nSet `general_settings.allow_client_side_credentials` to `false` so callers cannot override connection parameters, restrict proxy keys to trusted callers, and block the affected parameters (`api_base`, `base_url`, `model_list`, `fallbacks`, provider credential fields) at a reverse proxy or API gateway.",
  "id": "GHSA-3cv6-jpf6-8222",
  "modified": "2026-09-30T21:11:25Z",
  "published": "2026-09-30T21:11:25Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/BerriAI/litellm/security/advisories/GHSA-3cv6-jpf6-8222"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-84377"
    },
    {
      "type": "WEB",
      "url": "https://github.com/BerriAI/litellm/pull/36011"
    },
    {
      "type": "WEB",
      "url": "https://github.com/BerriAI/litellm/pull/36314"
    },
    {
      "type": "WEB",
      "url": "https://github.com/BerriAI/litellm/pull/36494"
    },
    {
      "type": "WEB",
      "url": "https://github.com/BerriAI/litellm/commit/473f72e63a9777d793fbbf57194d8ec4fb97bc1b"
    },
    {
      "type": "WEB",
      "url": "https://github.com/BerriAI/litellm/commit/820f247a6abba55cd87d130bef7bba7be3b29d37"
    },
    {
      "type": "WEB",
      "url": "https://github.com/BerriAI/litellm/commit/c898d341c02299cf2506d0d8e84cc67953043593"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/BerriAI/litellm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LiteLLM: Authenticated SSRF and provider-credential exfiltration via unvalidated request-body routing parameters"
}



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.



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.