Answer in brief
CVE-2026-77521 records a Critical severity (CVSS 10.0) vulnerability in MaxKB: Prompt-injectable agent can lead to command execution. The current sources do not mark it as known exploited. The current feed maps 1Panel-dev/MaxKB (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 10.0. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps 1Panel-dev/MaxKB (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| 1Panel-dev/MaxKBgeneric | <2.10.5-lts | 2.10.5-lts |
Published upstream
Sep 21, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 22, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Sep 21, 2026
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.
Quoted source text, attributed separately from HOL analysis.