openclaw (npm)< 2026.4.202026.4.20The agent-facing gateway config.patch / config.apply guard did not cover several operator-trusted settings, including sandbox policy, plugin enablement, gateway auth/TLS, hook routing, MCP server configuration, SSRF policy, and filesystem hardening. A prompt-injected model with access to the owner-only gateway tool could persist changes to those settings.
This is a model-to-operator guard bypass, not a remote unauthenticated gateway compromise. Severity is medium.
OpenClaw now blocks model-driven gateway config mutations for the broader operator-trusted path set and covers per-agent overrides and array-entry patching.
Fix commit:
fe30b31a97a917ecc6e92f6c85378b6b20352422Fixed in OpenClaw 2026.4.20.
{
"github_reviewed_at": "2026-04-25T23:51:11Z",
"github_reviewed": true,
"cwe_ids": [
"CWE-1220",
"CWE-285"
],
"nvd_published_at": null,
"severity": "MODERATE"
}