OpenClaw versions prior to 2026.2.2 contain an authorization bypass vulnerability where clients with operator.write scope can approve or deny exec approval requests by sending the /approve chat command. The /approve command path invokes exec.approval.resolve through an internal privileged gateway client, bypassing the operator.approvals permission check that protects direct RPC calls.

OpenClaw authorization bypass: operator.write can resolve exec approvals via chat.send -> /approve

Уязвимость сценария src/auto-reply/reply/commands-approve.ts ИИ-агента OpenClaw (ранее - ClawdBot или MoltBot), позволяющая нарушителю обойти существующие механизмы безопасности