CVE-2026-77521 (GCVE-0-2026-77521)

Vulnerability from cvelistv5 – Published: 2026-09-21 20:45 – Updated: 2026-09-22 13:32
VLAI
Title
MaxKB: Prompt-injectable agent can lead to command execution
Summary
MaxKB is an open-source AI assistant for enterprise. Prior to version 2.10.5-lts, assistants with a tool, MCP tool, skill, or sub-application use SandboxShellBackend, which exposes an execute shell tool without excluding it and omits execute from interrupt_on, so human approval is not required. Untrusted chat or ingested content can therefore cause command execution; source deployments with MAXKB_SANDBOX disabled run commands directly as the application user, while the official root container's string-based gosu wrapper allowed shell metacharacters to execute outside the intended sandbox. This issue is fixed in version 2.10.5-lts.
Severity
10 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
SSVC
Exploitation: poc Automatable: yes Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-22 13:31 UTC
CWE
  • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
  • CWE-250 - Execution with Unnecessary Privileges
  • CWE-749 - Exposed Dangerous Method or Function
Assigner
References
Impacted products
Vendor Product Version CPE status
1Panel-dev MaxKB Affected: < 2.10.5-lts
guessed Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-77521",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-22T13:31:58.194506Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-22T13:32:19.198Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "MaxKB",
          "vendor": "1Panel-dev",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 2.10.5-lts"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "MaxKB is an open-source AI assistant for enterprise. Prior to version 2.10.5-lts, assistants with a tool, MCP tool, skill, or sub-application use SandboxShellBackend, which exposes an execute shell tool without excluding it and omits execute from interrupt_on, so human approval is not required. Untrusted chat or ingested content can therefore cause command execution; source deployments with MAXKB_SANDBOX disabled run commands directly as the application user, while the official root container\u0027s string-based gosu wrapper allowed shell metacharacters to execute outside the intended sandbox. This issue is fixed in version 2.10.5-lts."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 10,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-78",
              "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-250",
              "description": "CWE-250: Execution with Unnecessary Privileges",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-749",
              "description": "CWE-749: Exposed Dangerous Method or Function",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-21T20:45:14.750Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx"
        },
        {
          "name": "https://github.com/1Panel-dev/MaxKB/commit/594f50f2ea80a502d1c955371ba0438b277c30ea",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/1Panel-dev/MaxKB/commit/594f50f2ea80a502d1c955371ba0438b277c30ea"
        },
        {
          "name": "https://github.com/1Panel-dev/MaxKB/releases/tag/v2.10.5-lts",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/1Panel-dev/MaxKB/releases/tag/v2.10.5-lts"
        }
      ],
      "source": {
        "advisory": "GHSA-f36j-f34j-h3rx",
        "discovery": "UNKNOWN"
      },
      "title": "MaxKB: Prompt-injectable agent can lead to command execution"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-77521",
    "datePublished": "2026-09-21T20:45:14.750Z",
    "dateReserved": "2026-08-20T20:23:02.507Z",
    "dateUpdated": "2026-09-22T13:32:19.198Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-77521",
      "date": "2026-09-22",
      "epss": "0.01049",
      "percentile": "0.62779"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "MaxKB",
                "vendor": "1Panel-dev",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 2.10.5-lts"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "MaxKB is an open-source AI assistant for enterprise. Prior to version 2.10.5-lts, assistants with a tool, MCP tool, skill, or sub-application use SandboxShellBackend, which exposes an execute shell tool without excluding it and omits execute from interrupt_on, so human approval is not required. Untrusted chat or ingested content can therefore cause command execution; source deployments with MAXKB_SANDBOX disabled run commands directly as the application user, while the official root container\u0027s string-based gosu wrapper allowed shell metacharacters to execute outside the intended sandbox. This issue is fixed in version 2.10.5-lts."
          }
        ],
        "id": "CVE-2026-77521",
        "lastModified": "2026-09-22T14:17:15.343",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 10.0,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 3.9,
              "impactScore": 6.0,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-77521",
                "options": [
                  {
                    "exploitation": "poc"
                  },
                  {
                    "automatable": "yes"
                  },
                  {
                    "technicalImpact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-22T13:31:58.194506Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-09-21T21:17:10.943",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/1Panel-dev/MaxKB/commit/594f50f2ea80a502d1c955371ba0438b277c30ea"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/1Panel-dev/MaxKB/releases/tag/v2.10.5-lts"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx"
          },
          {
            "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
            "url": "https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Deferred",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-78"
              },
              {
                "lang": "en",
                "value": "CWE-250"
              },
              {
                "lang": "en",
                "value": "CWE-749"
              }
            ],
            "source": "security-advisories@github.com",
            "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.



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.