What is the CVSS score of EUVD-2026-13016?

EUVD-2026-13016 has a CVSS 3.1 base score of 6.7 (Medium). CVSS vector: CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.0%.

Which versions of Openclaw are affected by EUVD-2026-13016?

Organizations using OpenClaw 2026.3.1 should be aware of notable risk from CVE-2026-29608 rated CVSS 6.7. Exploitation could compromise the security of affected deployments.. A patch is available.

How to fix or mitigate EUVD-2026-13016?

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

Openclaw EUVD-2026-13016

| CVE-2026-29608 MEDIUM

Improper Neutralization of Argument Delimiters in a Command ('Argument Injection') (CWE-88)

2026-03-19 VulnCheck

GHSA-h3rm-6x7g-882f

Information Disclosure Openclaw

6.7

CVSS 3.1 · NVD

Severity by source

NVD PRIMARY

6.7 MEDIUM

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

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

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

Attack Vector

Local

Attack Complexity

High

Privileges Required

Low

User Interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

EUVD ID Assigned

Mar 19, 2026 - 01:30 euvd

EUVD-2026-13016

Analysis Generated

Mar 19, 2026 - 01:30 vuln.today

Patch released

Mar 19, 2026 - 01:30 nvd

Patch available

CVE Published

Mar 19, 2026 - 01:00 nvd

MEDIUM 6.7

DescriptionCVE.org

OpenClaw 2026.3.1 contains an approval integrity vulnerability in system.run node-host execution where argv rewriting changes command semantics. Attackers can place malicious local scripts in the working directory to execute unintended code despite operator approval of different command text.

AnalysisAI

OpenClaw 2026.3.1 contains an approval integrity bypass vulnerability in the system.run node-host execution feature where attackers can rewrite command-line arguments (argv) to change the semantics of operator-approved commands. An authenticated local attacker with low privileges can place malicious scripts in the working directory to execute unintended code despite the operator approving different command text, resulting in high-impact confidentiality, integrity, and availability violations. A patch is available from the vendor, and no public exploit code has been widely reported, but the vulnerability represents a critical trust boundary violation in approval workflows.

Technical ContextAI

The vulnerability resides in OpenClaw's system.run node-host execution mechanism, which is responsible for executing shell commands on remote or local hosts as part of workflow automation. The root cause is classified under CWE-88 (Improper Neutralization of Argument Delimiters in a Command), indicating that the system fails to properly validate or neutralize user-controlled input that affects command argument parsing. When the system constructs and executes commands, it does not adequately prevent argv rewriting—an attacker can manipulate how arguments are parsed or interpreted, allowing shell metacharacters or path traversal techniques to redirect execution to attacker-controlled scripts in the working directory. This undermines the approval process because the operator approved a specific command string, but the actual executed command differs due to argument injection or rewriting. The affected product is OpenClaw (cpe:2.3:a:openclaw:openclaw:*:*:*:*:*:*:*:*), with the specific vulnerable version being 2026.3.1 and earlier releases.

RemediationAI

Upgrade OpenClaw to the patched version released by the vendor; the fix is available in commit dded569626b0d8e7bdab10b5e7528b6caf73a0f1 at https://github.com/openclaw/openclaw/commit/dded569626b0d8e7bdab10b5e7528b6caf73a0f1. Until patching is feasible, restrict command execution approvals to trusted operators only, implement strict working directory isolation to prevent local script injection, and enforce code review of all system.run commands before approval. Additionally, enable comprehensive audit logging of all command executions and their arguments to detect approval-to-execution mismatches, and consider implementing a secondary validation step that compares the approved command string byte-for-byte with the final executed command before invocation. Monitor the OpenClaw security advisory at https://www.vulncheck.com/advisories/openclaw-approval-integrity-bypass-via-system-run-argv-rewriting for updates and recommended patch timelines.