Command execution via truncated deep-link confirmation
Published Feb 19, 2026 · Updated Feb 19, 2026
UI misrepresentation in OpenClaw macOS desktop client 2026.2.6 through 2026.2.13 allows remote attackers to conceal agent commands. DeepLinkHandler showed only the first 240 characters of an unkeyed openclaw://agent message in its confirmation alert, then submitted the complete message after approval. Exploitation requires a user to select Run; resulting agent actions can reach arbitrary command execution only when configured tool approvals or allowlists permit it.
Summary
What happened
UI misrepresentation in OpenClaw macOS desktop client 2026.2.6 through 2026.2.13 allows remote attackers to conceal agent commands. DeepLinkHandler showed only the first 240 characters of an unkeyed openclaw://agent message in its confirmation alert, then submitted the complete message after approval. Exploitation requires a user to select Run; resulting agent actions can reach arbitrary command execution only when configured tool approvals or allowlists permit it.
The record
- CVE
- CVE-2026-26320
- Published
- Feb 19, 2026
- Updated
- Feb 19, 2026
- Vendor
- OpenClaw Foundation
- Product
- OpenClaw
- Classifications
- CWE-451, T1204.001
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Feb 19, 2026CVE publishedPublication date reported by the CVE source.
- Feb 19, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=>= 2026.2.6-0, < 2026.2.14
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo