OpenClaw 操作系统命令注入漏洞

OpenClaw is an open-source intelligent artificial assistant. OpenClaw has a vulnerability related to operating system command injection. This vulnerability stems from the exec-approvals permission list validation mechanism, which checks the argv tokens in a pre-expanded manner but actually execut...

The Most Common Swap Scams in 2026, and How to Avoid Them

Swap scams target traders through fake DEX sites, token approvals, and phishing. Learn how to detect swap scams and protect funds before you swap now...

Incorrect Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization via the system.run approvals. An attacker can cause execution of an unintended binary by crafting a command with a trailing-space in the executable token and...

OpenClaw: system.run approval identity mismatch could execute a different binary than displayed

Summary system.run approvals in OpenClaw used rendered command text as the approval identity while trimming argv token whitespace. Runtime execution still used raw argv. A crafted trailing-space executable token could therefore execute a different binary than what the approver saw. Affected...

OpenClaw: Gateway /tools/invoke tool escalation + ACP permission auto-approval

Summary OpenClaw Gateway exposes an authenticated HTTP endpoint POST /tools/invoke intended for invoking a constrained set of tools. Two issues could combine to significantly increase blast radius in misconfigured or exposed deployments: - The HTTP gateway layer did not deny high-risk session...

GHSA-943Q-MWMV-HHVH OpenClaw: Gateway /tools/invoke tool escalation + ACP permission auto-approval

Summary OpenClaw Gateway exposes an authenticated HTTP endpoint POST /tools/invoke intended for invoking a constrained set of tools. Two issues could combine to significantly increase blast radius in misconfigured or exposed deployments: - The HTTP gateway layer did not deny high-risk session...

OpenClaw Node system.run approval context-binding weakness in approval-enabled host=node flows

Summary In approval-enabled host=node workflows, system.run approvals did not always carry a strict, versioned execution-context binding. In uncommon setups that rely on these approvals as an integrity guardrail, a previously approved request could be reused with changed env input. Affected...

Incorrect Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization in the group allowlist authorization. An attacker can gain unauthorized access to group communications by leveraging DM pairing-store approvals to bypass explicit...

OpenClaw: system.run approvals did not bind PATH-token executable identity, enabling post-approval executable rebind

Summary For host=node runs, approvals validated command context but did not pin executable identity for non-path-like argv0 tokens for example tr. If PATH resolution changed after approval, execution could run a different binary. Impact A previously approved action could execute a different...

GHSA-Q399-23R3-HFX4 OpenClaw: system.run approvals did not bind PATH-token executable identity, enabling post-approval executable rebind

Summary For host=node runs, approvals validated command context but did not pin executable identity for non-path-like argv0 tokens for example tr. If PATH resolution changed after approval, execution could run a different binary. Impact A previously approved action could execute a different...

PT-2026-26233

Summary In the macOS companion app currently beta, a parsing mismatch in exec approvals could let shell-chain payloads pass allowlist checks in system.run under specific settings. Impact This path requires all of the following: - authenticated caller with operator.write - paired macOS beta node...

Command Injection

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Command Injection via the exec-approvals allowlist, when shell expansion is performed on argv tokens. An attacker can access sensitive files by supplying crafted arguments that leverage...

GHSA-XVHF-X56F-2HPP OpenClaw exec approvals: safeBins could bypass stdin-only constraints via shell expansion

Summary OpenClaw's exec-approvals allowlist supports a small set of "safe bins" intended to be stdin-only no positional file arguments when running tools.exec.host=gateway|node with security=allowlist. In affected configurations, the allowlist validation checked pre-expansion argv tokens, but...

OpenClaw exec approvals: safeBins could bypass stdin-only constraints via shell expansion

Summary OpenClaw's exec-approvals allowlist supports a small set of "safe bins" intended to be stdin-only no positional file arguments when running tools.exec.host=gateway|node with security=allowlist. In affected configurations, the allowlist validation checked pre-expansion argv tokens, but...

GHSA-H3F9-MJWJ-W476 OpenClaw Node host system.run rawCommand/command mismatch can bypass allowlist/approvals

Summary A mismatch between rawCommand and command in the node host system.run handler could cause allowlist/approval evaluation to be performed on one command while executing a different argv. Affected Configurations This only impacts deployments that: - Use the node host / companion node executi...

Incorrect Authorization

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Incorrect Authorization via the /approve command. An attacker can gain unauthorized approval or denial of pending execution requests by sending specially crafted chat messages through a...

OpenClaw authorization bypass: operator.write can resolve exec approvals via chat.send -> /approve

Summary What this means plain language If you give a client “chat/write” access to the gateway operator.write but you do not intend to let that client approve exec requests operator.approvals, affected versions could still let that client approve/deny a pending exec approval by sending the /appro...

GHSA-MQPW-46FH-299H OpenClaw authorization bypass: operator.write can resolve exec approvals via chat.send -> /approve

Summary What this means plain language If you give a client “chat/write” access to the gateway operator.write but you do not intend to let that client approve exec requests operator.approvals, affected versions could still let that client approve/deny a pending exec approval by sending the /appro...

GHSA-3HCM-GGVF-RCH5 OpenClaw has an exec allowlist bypass via command substitution/backticks inside double quotes

Summary Exec approvals allowlist bypass via command substitution/backticks inside double quotes. Affected Packages / Versions - Package: openclaw npm - Affected: = 2026.2.2 Impact Only affects setups that explicitly enable the optional exec approvals allowlist feature. Default installs are...

Command Injection

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Command Injection via the exec approvals allowlist when command substitution or backticks are used inside double quotes. An attacker can execute arbitrary commands by bypassing the intend...