GHSA-53MR-6C8Q-9789

Vulnerability from github – Published: 2026-04-03 21:59 – Updated: 2026-05-06 18:40
VLAI
Summary
LiteLLM: Privilege escalation via unrestricted proxy configuration endpoint
Details

Impact

The /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to do the following:

  • Modify proxy configuration and environment variables
  • Register custom pass-through endpoint handlers pointing to attacker-controlled Python code, achieving remote code execution
  • Read arbitrary server files by setting UI_LOGO_PATH and fetching via /get_image
  • Take over other priveleged accounts by overwriting UI_USERNAME and UI_PASSWORD environment variables

Patches

Fixed in v1.83.0. The endpoint now requires proxy_admin role.

Workarounds

Restrict API key distribution. There is no configuration-level workaround.

Severity
8.7 (High)
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:L/SI:L/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "litellm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.83.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-35029"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-863"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-03T21:59:31Z",
    "nvd_published_at": "2026-04-06T17:17:12Z",
    "severity": "HIGH"
  },
  "details": "### Impact\n\nThe `/config/update endpoint` does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to do the following:\n\n  - Modify proxy configuration and environment variables\n  - Register custom pass-through endpoint handlers pointing to attacker-controlled Python code, achieving remote code execution\n  - Read arbitrary server files by setting UI_LOGO_PATH and fetching via /get_image\n  - Take over other priveleged accounts by overwriting UI_USERNAME and UI_PASSWORD environment variables\n\n### Patches\n\nFixed in v1.83.0. The endpoint now requires `proxy_admin` role.\n\n### Workarounds\n\nRestrict API key distribution. There is no configuration-level workaround.",
  "id": "GHSA-53mr-6c8q-9789",
  "modified": "2026-05-06T18:40:45Z",
  "published": "2026-04-03T21:59:31Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/BerriAI/litellm/security/advisories/GHSA-53mr-6c8q-9789"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-35029"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/BerriAI/litellm"
    },
    {
      "type": "WEB",
      "url": "http://seclists.org/fulldisclosure/2026/Apr/17"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:L/SI:L/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "LiteLLM: Privilege escalation via unrestricted proxy configuration endpoint"
}



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.