MaxKB: Prompt-injectable agent can lead to command execution
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| 1Panel-dev | MaxKB | affected |
|
No data.
No data.
| Vendor | Product | Versions | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 1panel | Maxkb |
|
No CVSS v4.0
No CVSS v3.0
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: 1.0% (1.049% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
1panel
1panel maxkb |
|
| Vendors & Products |
1panel
1panel maxkb |
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | MaxKB: Prompt-injectable agent can lead to command execution | |
| Weaknesses | CWE-250 CWE-749 CWE-78 |
|
| References |
| |
| Metrics |
cvssV3_1
|