OpenClaw is a personal AI assistant. OpenClaw macOS desktop client registers the openclaw:// URL scheme. For openclaw://agent deep links without an unattended key, the app shows a confirmation dialog that previously displayed only the first 240 characters of the message, but executed the full message after the user clicked Run. At the time of writing, the OpenClaw macOS desktop client is still in beta. In versions 2026.2.6 through 2026.2.13, an attacker could pad the message with whitespace to push a malicious payload outside the visible preview, increasing the chance a user approves a different message than the one that is actually executed. If a user runs the deep link, the agent may perform actions that can lead to arbitrary command execution depending on the users configured tool approvals/allowlists. This is a social-engineering mediated vulnerability: the confirmation prompt could be made to misrepresent the executed message. The issue is fixed in 2026.2.14. Other mitigations include not approve unexpected Run OpenClaw agent? prompts triggered while browsing untrusted sites and usingunattended deep links only with a valid key for trusted personal automations.
The user interface (UI) does not properly represent critical information to the user, allowing the information - or its source - to be obscured or spoofed. This is often a component in phishing attacks.
If an attacker can cause the UI to display erroneous data, or to otherwise convince the user to display information that appears to come from a trusted source, then the attacker could trick the user into performing the wrong action. This is often a component in phishing attacks, but other kinds of problems exist. For example, if the UI is used to monitor the security state of a system or network, then omitting or obscuring an important indicator could prevent the user from detecting and reacting to a security-critical event. UI misrepresentation can take many forms: