CVE-2026-59821 (GCVE-0-2026-59821)

Vulnerability from cvelistv5 – Published: 2026-07-08 19:14 – Updated: 2026-07-09 14:38
VLAI
Title
LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks
Summary
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM's Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable.
Severity
2.1 (Low)
CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N
SSVC
Exploitation: none Automatable: no Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-07-09 14:38 UTC
CWE
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
Assigner
GitHub_M CNA under the mitre root
CNA scorecard C 72/100 over 7867 records in the last 180 days details
References
Impacted products
Vendor Product Version CPE status
BerriAI litellm Affected: < 1.82.0-stable
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-59821",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-07-09T14:38:04.002799Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-07-09T14:38:09.991Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "litellm",
          "vendor": "BerriAI",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.82.0-stable"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM\u0027s Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 2.1,
            "baseSeverity": "LOW",
            "privilegesRequired": "HIGH",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "LOW",
            "vulnConfidentialityImpact": "LOW",
            "vulnIntegrityImpact": "LOW"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-07-08T19:14:13.265Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278"
        },
        {
          "name": "https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba"
        },
        {
          "name": "https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable"
        }
      ],
      "source": {
        "advisory": "GHSA-72m8-9m7m-h278",
        "discovery": "UNKNOWN"
      },
      "title": "LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-59821",
    "datePublished": "2026-07-08T19:14:13.265Z",
    "dateReserved": "2026-07-07T15:00:50.978Z",
    "dateUpdated": "2026-07-09T14:38:09.991Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-59821",
      "date": "2026-10-28",
      "epss": "0.00904",
      "percentile": "0.59665"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "litellm",
                "vendor": "BerriAI",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 1.82.0-stable"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "8A63F050-5E87-4156-B90C-1A01326E2C3B",
                    "versionEndExcluding": "1.82.0",
                    "vulnerable": true
                  },
                  {
                    "criteria": "cpe:2.3:a:litellm:litellm:1.82.0:nightly:*:*:*:*:*:*",
                    "matchCriteriaId": "D5B44E64-DDBE-4615-83B4-98B957713B1F",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM\u0027s Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable."
          },
          {
            "lang": "es",
            "value": "LiteLLM es un servidor proxy (Pasarela de IA) para llamar a las API de LLM en formato OpenAI (o nativo). Antes de la versi\u00f3n 1.82.0-stable, las rutas de creaci\u00f3n y actualizaci\u00f3n de producci\u00f3n de las barreras de seguridad de c\u00f3digo personalizado de LiteLLM no aplicaban el mismo sandboxing y validaci\u00f3n utilizados por el punto final de prueba, lo que permit\u00eda a un usuario privilegiado con acceso para crear o actualizar barreras de seguridad enviar c\u00f3digo Python personalizado que se ejecutaba en el entorno proxy de LiteLLM y pod\u00eda exponer secretos disponibles para el proceso. Este problema est\u00e1 solucionado en la versi\u00f3n 1.82.0-stable."
          }
        ],
        "id": "CVE-2026-59821",
        "lastModified": "2026-10-25T17:10:00.197",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 7.2,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "HIGH",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 1.2,
              "impactScore": 5.9,
              "source": "nvd@nist.gov",
              "type": "Primary"
            }
          ],
          "cvssMetricV40": [
            {
              "cvssData": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "PRESENT",
                "attackVector": "NETWORK",
                "availabilityRequirement": "NOT_DEFINED",
                "baseScore": 2.1,
                "baseSeverity": "LOW",
                "confidentialityRequirement": "NOT_DEFINED",
                "exploitMaturity": "NOT_DEFINED",
                "integrityRequirement": "NOT_DEFINED",
                "modifiedAttackComplexity": "NOT_DEFINED",
                "modifiedAttackRequirements": "NOT_DEFINED",
                "modifiedAttackVector": "NOT_DEFINED",
                "modifiedPrivilegesRequired": "NOT_DEFINED",
                "modifiedSubAvailabilityImpact": "NOT_DEFINED",
                "modifiedSubConfidentialityImpact": "NOT_DEFINED",
                "modifiedSubIntegrityImpact": "NOT_DEFINED",
                "modifiedUserInteraction": "NOT_DEFINED",
                "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
                "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
                "modifiedVulnIntegrityImpact": "NOT_DEFINED",
                "privilegesRequired": "HIGH",
                "providerUrgency": "NOT_DEFINED",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "valueDensity": "NOT_DEFINED",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:L/VI:L/VA:L/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",
                "version": "4.0",
                "vulnAvailabilityImpact": "LOW",
                "vulnConfidentialityImpact": "LOW",
                "vulnIntegrityImpact": "LOW",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-59821",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-07-09T14:38:04.002799Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-07-08T20:16:57.547",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Patch"
            ],
            "url": "https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Product",
              "Release Notes"
            ],
            "url": "https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Mitigation",
              "Patch",
              "Vendor Advisory"
            ],
            "url": "https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-94"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "aggregate_severity": "Important",
      "current_release_date": "2026-07-13T13:56:31+00:00",
      "cve": "CVE-2026-59821",
      "id": "CVE-2026-59821",
      "initial_release_date": "2026-07-08T19:14:13.265000+00:00",
      "product_status:known_not_affected": "7",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "litellm: LiteLLM: Arbitrary code execution and information disclosure via custom code guardrails",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-59821.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-59821",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-07-09T14:38:04.002799Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-07-09T14:38:07.032Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "litellm",
              "vendor": "BerriAI",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 1.82.0-stable"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.82.0-stable, LiteLLM\u0027s Custom Code Guardrails production create and update paths did not apply the same sandboxing and validation used by the test endpoint, allowing a privileged user with access to create or update guardrails to submit custom Python code that executed in the LiteLLM proxy environment and could expose secrets available to the process. This issue is fixed in version 1.82.0-stable."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "attackComplexity": "LOW",
                "attackRequirements": "PRESENT",
                "attackVector": "NETWORK",
                "baseScore": 2.1,
                "baseSeverity": "LOW",
                "privilegesRequired": "HIGH",
                "subAvailabilityImpact": "NONE",
                "subConfidentialityImpact": "NONE",
                "subIntegrityImpact": "NONE",
                "userInteraction": "NONE",
                "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "LOW",
                "vulnConfidentialityImpact": "LOW",
                "vulnIntegrityImpact": "LOW"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-94",
                  "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-07-08T19:14:13.265Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/BerriAI/litellm/security/advisories/GHSA-72m8-9m7m-h278"
            },
            {
              "name": "https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/BerriAI/litellm/commit/e50b4486d0f7aa0497185a1ebcdd2c91f1769eba"
            },
            {
              "name": "https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/BerriAI/litellm/releases/tag/v1.82.0-stable"
            }
          ],
          "source": {
            "advisory": "GHSA-72m8-9m7m-h278",
            "discovery": "UNKNOWN"
          },
          "title": "LiteLLM: Custom Code Guardrails production endpoints bypass code safety checks"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-59821",
        "datePublished": "2026-07-08T19:14:13.265Z",
        "dateReserved": "2026-07-07T15:00:50.978Z",
        "dateUpdated": "2026-07-09T14:38:09.991Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

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.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON

Loading timeline…




    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.