CVE-2026-26320

CVE-2026-26320 is a medium-severity vulnerability in Openclaw with a CVSS 3.x base score of 6.5. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-451.

Key facts

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.

Frequently asked questions

What is CVE-2026-26320?
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.
How severe is CVE-2026-26320?
CVE-2026-26320 has a CVSS 3.x base score of 6.5, rated medium severity. It is exploitable over network with low attack complexity, requires no privileges and user interaction. Impact on confidentiality is none, integrity high, and availability none.
Is CVE-2026-26320 being actively exploited?
It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (34th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2026-26320?
CVE-2026-26320 affects Openclaw. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2026-26320?
Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
Does CVE-2026-26320 have an EU (EUVD) identifier?
Yes. CVE-2026-26320 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-8431.
When was CVE-2026-26320 published?
CVE-2026-26320 was published on 2026-02-19 and last updated on 2026-06-17.

References

Affected products (1)

More vulnerabilities in Openclaw

All CVEs affecting Openclaw →

Other CWE-451 vulnerabilities

Browse all CWE-451 vulnerabilities →