CVE-2026-77521 MaxKB: Prompt-injectable agent can lead to command execution
Attackers can execute arbitrary commands via prompt injection in MaxKB AI assistants when sandboxing is disabled or misconfigured.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-77521?
CVE-2026-77521 is a critical command injection vulnerability in 1Panel-dev MaxKB, published on 21 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Which versions are affected by CVE-2026-77521?
How do I fix CVE-2026-77521?
No fix has been published for CVE-2026-77521 yet. Limit exposure of the affected software until one is available.
Upgrade, and pass arguments to programs as a list instead of through a shell. More about Command injection.
Is CVE-2026-77521 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-77521 exists.
Public exploit code: 1 proofs of concept on GitHub.
Sources
Also known as GHSA-f36j-f34j-h3rx.