PT-2026-28457

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.3.11 Description The software contains an approval integrity issue where system.run approvals do not properly bind mutable file operands for specific script runners, including tsx and jiti. This allows attackers...

PT-2026-28458

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.3.11 Description The software contains an approval integrity issue that allows attackers to execute modified local code. This occurs by altering scripts between the approval stage and execution, specifically whe...

OpenClaw 安全漏洞

OpenClaw is a command line tool for rights management. A security vulnerability exists in versions of OpenClaw prior to 2026.3.11, which stems from the failure of the system.run approval function to properly bind variable file operands for specific script runners such as tsx, jiti, and others. An...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

OpenClaw: Silent privilege escalation via gateway shared-auth reconnect

Summary Gateway local shared-auth reconnect silently widens paired device scope from operator.read to operator.admin and reach node RCE Affected Packages / Versions - Package: openclaw - Affected versions: = 2026.3.24 - First patched version: 2026.3.25 - Latest published npm version at verificati...

EUVD-2026-16602

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-30304

AI Code’s CVE-2026-30304 stems from its design that auto-executes commands deemed safe while requiring approval for potentially destructive ones. Multiple trusted sources describe a prompt-injection flaw: an attacker can wrap malicious commands in a generic template and fool the model into classi...

CVE-2026-30302

The command auto-approval module in CodeRider-Kilo contains an OS Command Injection vulnerability, rendering its whitelist security mechanism ineffective. The vulnerability stems from the incorrect use of an incompatible command parser the Unix-based shell-quote library to analyze commands on the...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

PT-2026-28397

Name of the Vulnerable Software and Affected Versions AI Code affected versions not specified Description The software’s design, which includes options for executing safe and all commands, is susceptible to prompt injection attacks. The system is intended to automatically execute commands deemed...

PT-2026-28396

Name of the Vulnerable Software and Affected Versions Axon Code affected versions not specified Description The command auto-approval module contains an OS Command Injection issue, bypassing its whitelist security mechanism. This is due to the use of an incompatible command parser the Unix-based...

CVE-2026-30302

The command auto-approval module in CodeRider-Kilo contains an OS Command Injection vulnerability, rendering its whitelist security mechanism ineffective. The vulnerability stems from the incorrect use of an incompatible command parser the Unix-based shell-quote library to analyze commands on the...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

GHSA-HF68-49FM-59CQ OpenClaw Gateway: RCE and Privilege Escalation from operator.pairing to operator.admin via device.pair.approve

Summary device.pair.approve allowed an operator.pairing approver to approve a pending device request for broader operator scopes than the approver actually held. Affected Packages / Versions - Package: openclaw npm - Affected: = 2026.3.22 - Latest released tag checked: v2026.3.23-2...

CVE-2026-32058

OpenClaw versions prior to 2026.2.26 contain an approval context-binding weakness in system.run execution flows with host=node that allows reuse of previously approved requests with modified environment variables. Attackers with access to an approval id can exploit this by reusing an approval wit...

CVE-2026-27183

OpenClaw versions prior to 2026.3.7 contain a shell approval gating bypass vulnerability in system.run dispatch-wrapper handling that allows attackers to skip shell wrapper approval requirements. The approval classifier and execution planner apply different depth-boundary rules, permitting exactl...

CVE-2026-31991

OpenClaw versions prior to 2026.2.26 contain an authorization bypass vulnerability where Signal group allowlist policy incorrectly accepts sender identities from DM pairing-store approvals. Attackers can exploit this boundary weakness by obtaining DM pairing approval to bypass group allowlist...

CVE-2026-29608

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...