What is the CVSS score of CVE-2026-32052?

CVE-2026-32052 has a CVSS 3.1 base score of 6.4 (Medium). CVSS vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:H/A:H. EPSS exploitation probability: 0.2%.

Which versions of Openclaw are affected by CVE-2026-32052?

CVE-2026-32052 presents moderate security risk rated CVSS 6.4. Exploitation could compromise the security of affected deployments. Proof-of-concept code is publicly available.. A patch is available.

Is there a public PoC exploit available for CVE-2026-32052?

Yes, a public proof-of-concept exploit is available for CVE-2026-32052. Prioritise patching immediately. EPSS: 0.2%.

How to fix or mitigate CVE-2026-32052?

Within 30 days: Identify affected systems and apply vendor patches as part of regular patch cycle. Vendor patch is available.

Openclaw CVE-2026-32052

EUVD-2026-13951 MEDIUM

Interpretation Conflict (CWE-436)

2026-03-21 VulnCheck

Command Injection Openclaw

6.4

CVSS 3.1 · NVD

Severity by source

NVD PRIMARY

6.4 MEDIUM

AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:H/A:H

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:H/A:H

Attack Vector

Network

Attack Complexity

High

Privileges Required

Low

User Interaction

Required

Scope

Unchanged

Confidentiality

None

Integrity

High

Availability

High

Lifecycle Timeline

PoC Detected

Mar 23, 2026 - 17:07 vuln.today

Public exploit code

EUVD ID Assigned

Mar 21, 2026 - 01:00 euvd

EUVD-2026-13951

Analysis Generated

Mar 21, 2026 - 01:00 vuln.today

Patch released

Mar 21, 2026 - 01:00 nvd

Patch available

CVE Published

Mar 21, 2026 - 00:42 nvd

MEDIUM 6.4

Blast Radius

ecosystem impact

† from your stack dependencies † transitive graph · vuln.today resolves 4-path depth

1 npm packages depend on openclaw (1 direct, 0 indirect)

Ecosystem-wide dependent count for version 2026.2.24.

DescriptionCVE.org

OpenClaw versions prior to 2026.2.24 contain a command injection vulnerability in the system.run shell-wrapper that allows attackers to execute hidden commands by injecting positional argv carriers after inline shell payloads. Attackers can craft misleading approval text while executing arbitrary commands through trailing positional arguments that bypass display context validation.

AnalysisAI

OpenClaw versions before 2026.2.24 allow authenticated attackers to execute arbitrary commands through command injection in the system.run shell-wrapper by injecting malicious arguments that bypass validation controls. Public exploit code exists for this vulnerability, enabling attackers to disguise malicious payloads while executing hidden commands with the privileges of the affected application.

Technical ContextAI

The vulnerability exists in OpenClaw's shell-wrapper implementation (system.run function) which improperly handles positional command-line arguments. The root cause is classified under CWE-436 (Untrusted Input in Format String) and involves insufficient validation of argument boundaries and display context. Attackers exploit this by injecting trailing positional arguments that are processed by the shell interpreter after the visible inline payload, allowing hidden command execution. The affected product is OpenClaw (CPE: cpe:2.3:a:openclaw:openclaw:*:*:*:*:*:*:*:*), and the vulnerability specifically impacts versions before 2026.2.24. The shell-wrapper's failure to properly sanitize or isolate positional arguments from user-controlled input creates a classic command injection condition where an attacker can append shell metacharacters or additional commands that execute outside the intended command scope.

RemediationAI

Upgrade OpenClaw to version 2026.2.24 or later immediately. The vendor has released patches available via GitHub commits 0f0a680d3df81739ea5088a2f88e65f938b7936b and 55cf92578d266987e390c4bf688196af98eac748, which can be reviewed at https://github.com/openclaw/openclaw. If immediate patching is not feasible, restrict OpenClaw access to trusted users only and implement strict approval workflows that validate the full command context before execution. Additionally, deploy network segmentation to limit OpenClaw's exposure to authenticated users and consider disabling or sandboxing the system.run function until patching is complete. Monitor logs for suspicious positional argument injection patterns such as trailing semicolons, pipes, or command substitution syntax in approval requests.