CVE-2026-26320
Received
Received - Intake
Command Injection via Incomplete URL Scheme Confirmation in OpenClaw
Publication date: 2026-02-19
Last updated on: 2026-02-20
Assigner: GitHub, Inc.
Description
Description
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 user's 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.
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| openclaw | openclaw | From 2026.2.6 (inc) to 2026.2.14 (exc) |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-451 | 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. |