OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.5.18 contained security vulnerabilities. These vulnerabilities stemmed from the fact that extension metadata during market runtime could be redirected to load into unscanned packa...

Compromise OpenClaw with Prompt Injections in Message Objects

Executive Summary As powerful personal AI assistants become increasingly widespread, their ability to access tools, files, and external services also makes them susceptible to prompt injection attacks, where malicious content can manipulate their behavior. This research evaluated OpenClaw against...

The vulnerability of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) relates to the use of an incomplete black list, which allows a perpetrator to execute arbitrary code.

The vulnerability of the AI agent OpenClaw formerly known as ClawdBot or MoltBot is related to the use of an incomplete black list. Exploiting this vulnerability allows a remote attacker to execute arbitrary code...

The vulnerability of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) arises from an improper authorization process based on a list of permitted senders. This allows attackers to bypass existing security mechanisms.

The vulnerability of the AI agent OpenClaw formerly known as ClawdBot or MoltBot is related to an incorrect authorization process based on a list of permitted senders. Exploiting this vulnerability could allow a hacker to bypass existing security mechanisms...

The vulnerability of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) arises from synchronization errors when using a shared resource. This vulnerability allows attackers to bypass existing security mechanisms and gain unauthorized access to protected information.

The vulnerability of the AI agent OpenClaw formerly known as ClawdBot or MoltBot is related to synchronization errors when using a shared resource. Exploiting this vulnerability allows a malicious actor to bypass existing security mechanisms and gain unauthorized access to protected information...

The vulnerability of the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) relates to synchronization errors when using a shared resource. This vulnerability allows a hacker to bypass existing security mechanisms and execute arbitrary code.

The vulnerability of the AI agent OpenClaw formerly known as ClawdBot or MoltBot is related to synchronization errors when using a shared resource. Exploiting this vulnerability allows a remote attacker to bypass existing security mechanisms and execute arbitrary code...

The vulnerability of the Tlon plugin (Urbit), which targets the AI agent OpenClaw (previously ClawdBot or MoltBot), allows a hacker to perform an SSRF attack.

The vulnerability of the Tlon plugin Urbit, which is part of the AI agent OpenClaw previously known as ClawdBot or MoltBot, stems from insufficient validation of requests on the server side. Exploiting this vulnerability allows a remote attacker to execute an SSRF attack...

The vulnerability of the `tunnel.allowNgrokFreeTierLoopbackBypass` parameter. This vulnerability is exploited by an AI agent named OpenClaw (previously known as ClawdBot or MoltBot), allowing attackers to compromise the integrity and accessibility of protected information.

The vulnerability of the tunnel.allowNgrokFreeTierLoopbackBypass parameter is related to the AI agent OpenClaw previously ClawdBot or MoltBot. This vulnerability stems from the lack of authentication for a critical function. Exploiting this vulnerability allows an attacker operating remotely to...

The vulnerability of the OAuth authorization protocol implemented by the AI agent OpenClaw (formerly known as ClawdBot or MoltBot) allows a attacker to perform a CSRF attack.

The vulnerability of the OAuth authorization protocol implementation of the AI agent OpenClaw formerly known as ClawdBot or MoltBot is related to the manipulation of cross-site requests. Exploiting this vulnerability allows a malicious actor to perform a CSRF attack remotely...

The vulnerability in the `src/auto-reply/reply/commands-approve.ts` script of the AI agent OpenClaw (previously known as ClawdBot or MoltBot) allows a violator to bypass existing security mechanisms.

The vulnerability in the src/auto-reply/reply/commands-approve.ts script of the AI agent OpenClaw previously known as ClawdBot or MoltBot is related to deficiencies in the authentication process. Exploiting this vulnerability could allow a malicious actor to bypass existing security mechanisms...

CVE-2026-6011

A weakness has been identified in OpenClaw up to 2026.1.26. Affected by this issue is some unknown functionality of the file src/agents/tools/web-fetch.ts of the component assertPublicHostname Handler. Executing a manipulation can lead to server-side request forgery. The attack can be executed...

CVE-2026-8305

A vulnerability was detected in OpenClaw up to 2026.1.24. The impacted element is the function handleBlueBubblesWebhookRequest of the file extensions/bluebubbles/src/monitor.ts of the component bluebubbles Webhook. Performing a manipulation results in improper authentication. It is possible to...

CVE-2026-35673

OpenClaw before 2026.4.29 contains an SSRF policy bypass vulnerability in browser debug and export routes that allows reuse of already-open blocked tabs. Attackers with access to these routes can bypass private-network SSRF policies by reusing blocked tabs to export or inspect content that should...

CVE-2026-32905

OpenClaw before 2026.5.4 contains an authorization bypass vulnerability in the bundled device-pair plugin that allows non-owner authorized chat senders to issue device-pairing bootstrap codes without proper scope validation. Attackers with chat command access can create setup codes to enroll...

CVE-2026-45004

OpenClaw before 2026.4.23 contains an arbitrary code execution vulnerability in the bundled plugin setup resolver that loads setup-api.js from process.cwd during provider setup metadata resolution. Attackers can execute arbitrary JavaScript under the current user account by placing a malicious...

CVE-2026-45006

OpenClaw before 2026.4.23 contains an improper access control vulnerability in the gateway tool's config.apply and config.patch operations that allows compromised models to write unsafe configuration changes by bypassing an incomplete denylist protection. Attackers can persist malicious config...

CVE-2026-44115

OpenClaw before 2026.4.22 contains an exec allowlist analysis vulnerability allowing shell expansion hiding in unquoted heredoc bodies. Attackers can bypass allowlist validation by embedding shell expansion tokens in heredoc bodies to execute unapproved commands at runtime...

CVE-2026-35674

OpenClaw before 2026.5.18 contains a scope bypass vulnerability in the Gateway chat.send route that allows scoped clients to execute privileged commands. Attackers with operator.write scope can deliver commands through inherited external routes to bypass operator.approvals and operator.admin scop...

CVE-2026-32906

OpenClaw before 2026.5.12 contains a privilege escalation vulnerability in Slack plugin approvals that allows exec-authorized users to resolve plugin approvals through the exec approver gate. Attackers with limited exec approval permissions can bypass intended approval splits to approve plugin...

CVE-2026-35630

OpenClaw before 2026.5.18 contains an authorization bypass vulnerability in QQBot native approval buttons that fails to enforce configured approver identity. Non-approver users can click approval buttons to resolve pending exec or plugin approval requests without proper authorization...