CVE-2026-26320
OpenClaw macOS deep link confirmation truncation can conceal executed agent message
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- Passive
What an attacker can affect
- Confidentiality
- None
- Integrity
- High
- Availability
- None
Exploit likelihood
What each source reports
CVE List Score used
OpenClaw macOS deep link confirmation truncation can conceal executed agent message
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.
- Record
CVE-2026-26320- CVSS 4.0
- 7.1 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N - Weakness
- CWE-451
- Updated
- 2026-11-02
EUVDEUVD-2026-8431
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.
- Record
EUVD-2026-8431- CVSS 4.0
- 7.1 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-7q2j-c4q5-rm27
OpenClaw macOS deep link confirmation truncation can conceal executed agent message
Summary
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.
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.
Impact
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.
Affected Versions
- OpenClaw macOS desktop client versions >= 2026.2.6 and <= 2026.2.13.
Fixed Versions
- 2026.2.14.
Mitigations
- Do not approve unexpected "Run OpenClaw agent?" prompts triggered while browsing untrusted sites.
- Use unattended deep links only with a valid
keyfor trusted personal automations.
Resolution
Unkeyed deep links now enforce a strict message length limit for confirmation and ignore delivery/routing knobs (deliver, to, channel) unless a valid unattended key is provided.
Fix commit: 28d9dd7a772501ccc3f71457b4adfee79084fe6f
Fix commit 28d9dd7a772501ccc3f71457b4adfee79084fe6f confirmed on main and in v2026.2.14. Upgrade to openclaw >= 2026.2.14.
- Record
GHSA-7q2j-c4q5-rm27- CVSS 4.0
- 7.1 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N - Weakness
- CWE-451
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2026-26320- CVSS 4.0
- 7.1 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - CVSS 3.1
- 6.5 Medium
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N - Weakness
- CWE-451
- Updated
- 2026-11-02
OSV
OpenClaw macOS deep link confirmation truncation can conceal executed agent message
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.
- Record
CVE-2026-26320- CVSS 4.0
- 7.1 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N - Weakness
- CWE-451
- Updated
- 2026-11-02
OSVGHSA-7q2j-c4q5-rm27
OpenClaw macOS deep link confirmation truncation can conceal executed agent message
Summary
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.
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.
Impact
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.
Affected Versions
- OpenClaw macOS desktop client versions >= 2026.2.6 and <= 2026.2.13.
Fixed Versions
- 2026.2.14.
Mitigations
- Do not approve unexpected "Run OpenClaw agent?" prompts triggered while browsing untrusted sites.
- Use unattended deep links only with a valid
keyfor trusted personal automations.
Resolution
Unkeyed deep links now enforce a strict message length limit for confirmation and ignore delivery/routing knobs (deliver, to, channel) unless a valid unattended key is provided.
Fix commit: 28d9dd7a772501ccc3f71457b4adfee79084fe6f
Fix commit 28d9dd7a772501ccc3f71457b4adfee79084fe6f confirmed on main and in v2026.2.14. Upgrade to openclaw >= 2026.2.14.
- Record
GHSA-7q2j-c4q5-rm27- CVSS 4.0
- 7.1 High
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N - Weakness
- CWE-451
- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
openclawnpm | 2026.2.6-0 up to 2026.2.14 | 2026.2.14 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-26320 is a high vulnerability (CVSS 7.1) in Openclaw, published February 17, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.49%, the 42nd percentile. Fixed in openclaw 2026.2.14.
References
github.com/openclaw/openclaw/security/advisories/GHSA-7q2j-c4q5-rm27
nvd.nist.gov/vuln/detail/CVE-2026-26320