Skip to content
Fencer Intel
critical 10.0

CVE-2026-77521 json

MaxKB: Prompt-injectable agent can lead to command execution

published 2mo ago modified last mo. also EUVD-2026-84161 , GHSA-f36j-f34j-h3rx

Unreviewed: the maintainers' own advisory

Published by the maintainers on their GitHub repository 1Panel-dev/MaxKB. GitHub has not reviewed it into the GitHub Advisory Database, so the affected packages and versions are the maintainers' word. Read the full advisory on GitHub.

cvss
10.0
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
1.0%
EPSS 1.0% chance of exploitation in 30 days, percentile 64%
public exploits
0
none known

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.

Patch / fix

  • maxkb maxkb 2.10.5-lts

Is CVE-2026-77521 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
total
Assessed
last mo.

Exploit prediction

1.05% chance of exploitation in the next 30 days, higher than 64% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/1Panel-dev/MaxKB/security/advisories/GHSA-f36j-f34j-h3rx referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 10.0 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Affected products

  • 1Panel-dev MaxKB

Classification

Weakness
  • CWE-78 Improper Neutralization of Special Elements used in an OS Command
  • CWE-250 Execution with Unnecessary Privileges
  • CWE-749 Exposed Dangerous Method or Function

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

The maintainers of 1Panel-dev/MaxKB published their own advisory on GitHub. Reviewed sources take precedence over it.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.