{"id":"CVE-2026-77521","published":"2026-09-21T21:17:10.943","lastModified":"2026-09-22T14:17:15.343","description":"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.","cvssScore":10,"cvssSeverity":"CRITICAL","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","cwes":["CWE-78","CWE-250","CWE-749"],"vendors":[],"products":[],"references":[{"url":"https://github.com/1Panel-dev/MaxKB/commit/594f50f2ea80a502d1c955371ba0438b277c30ea","tags":[]},{"url":"https://github.com/1Panel-dev/MaxKB/releases/tag/v2.10.5-lts","tags":[]},{"url":"https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx","tags":[]},{"url":"https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx","tags":[]}],"exploitRefs":[{"url":"https://github.com/1Panel-dev/MaxKB/commit/594f50f2ea80a502d1c955371ba0438b277c30ea","tags":[]},{"url":"https://github.com/1Panel-dev/MaxKB/releases/tag/v2.10.5-lts","tags":[]},{"url":"https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx","tags":[]},{"url":"https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx","tags":[]}],"hasPoc":true,"ai":{"summary":"The flaw allows untrusted chat or content to execute arbitrary shell commands, posing a significant risk to system security.","exploitability":"Exploitation is relatively easy given untrusted input, requiring only the presence of the affected MCP tool or skill.","blast_radius":"If exploited, this could lead to complete system compromise, allowing attackers to execute arbitrary commands as the application user or root.","remediation":"Upgrade to version 2.10.5-lts or later.","detection":"No reliable host or network indicator is derivable from the published description.","tags":["rce","shell-exec","ai","open-source"],"model":"qwen2.5:7b-instruct","analyzedAt":"2026-09-27T08:54:22.680Z"}}