PT-2026-39682

OpenClaw before 2026.4.20 contains a message classification vulnerability in Feishu card-action callbacks that misclassifies direct messages as group conversations. Attackers can bypass dmPolicy enforcement by triggering card-action flows in direct message conversations that should have been...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.20 contained security vulnerabilities. These vulnerabilities were due to tool policy bypassing, which could allow bundled MCP and LSP tools to circumvent configuration-based too...

PT-2026-39693

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...

PT-2026-39692

OpenClaw before 2026.4.22 allows workspace dotenv files to override connector endpoint hosts for Matrix, Mattermost, IRC, and Synology connectors. Attackers with workspace access can redirect runtime traffic to malicious endpoints by setting endpoint variables in dotenv files...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw from 2026.4.5 to 2026.4.20 contained a security vulnerability. This vulnerability was caused by environmental variable injection, which could lead to the dotenv workspace overriding...

PT-2026-39685

OpenClaw before 2026.4.15 contains an arbitrary local file read vulnerability in the webchat audio embedding helper that fails to apply local media root containment checks. Attackers can influence agent or tool-produced ReplyPayload.mediaUrl parameters to resolve absolute local paths or file URLs...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.22 contained security vulnerabilities. These vulnerabilities were caused by bypassing security envelope constraints, which could lead to ACP sub-sessions that failed to inherit...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.20 contained security vulnerabilities. These vulnerabilities stemmed from a flaw related to hook session keys, which could allow attackers to bypass the...

PT-2026-39703

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...

PT-2026-39694

OpenClaw before 2026.4.23 caches resolved webhook route secrets backed by SecretRef values, allowing stale secrets to remain valid after rotation and reload. Attackers with previously valid webhook route secrets can continue authenticating requests and invoking configured webhook task flows until...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.23 contained security vulnerabilities. These vulnerabilities stemmed from caching resolved webhook routing keys supported by SecretRef values, allowing expired keys to remain...

CVE-2026-44112

OpenClaw before 2026.4.22 contains a time-of-check/time-of-use race condition in OpenShell sandbox filesystem writes that allows attackers to redirect writes outside the intended mount root. Attackers can exploit symlink swaps during filesystem operations to bypass sandbox restrictions and write...

CVE-2026-44111

OpenClaw before 2026.4.15 contains an arbitrary file read vulnerability in the QMD backend memoryget function that allows callers to read any Markdown files within the workspace root. Attackers with access to the memory tool can bypass path restrictions by providing arbitrary workspace Markdown...

CVE-2026-43579

OpenClaw before 2026.4.10 contains an insufficient access control vulnerability in Nostr plugin HTTP profile routes that allows operators with write permissions to persist profile configuration without requiring admin authority. Attackers with operator.write scope can modify Nostr profile setting...

CVE-2026-44114

OpenClaw before 2026.4.20 fails to properly reserve the OPENCLAW runtime-control environment namespace in workspace dotenv files, allowing attackers to override critical runtime variables. Malicious workspaces can set variables like OPENCLAWGITDIR to manipulate trusted OpenClaw runtime behavior...

CVE-2026-44116

OpenClaw before 2026.4.22 contains a server-side request forgery vulnerability in the Zalo plugin's sendPhoto function that fails to validate outbound photo URLs through the SSRF guard. Attackers can bypass SSRF protection by providing malicious photo URLs to the Zalo Bot API, enabling unauthoriz...

CVE-2026-43583

OpenClaw versions 2026.4.10 before 2026.4.14 fail to persist session context during delivery queue recovery for media replay. Attackers can exploit recovered queued outbound media to bypass group tool policy enforcement and weaken channel media restrictions after service restart or recovery...

CVE-2026-44118

OpenClaw before 2026.4.22 derives loopback MCP owner context from spoofable server-issued bearer tokens in request headers. Non-owner loopback clients can present themselves as owner to bypass owner-gated operations by manipulating the sender-owner header metadata...

CVE-2026-43575

OpenClaw versions 2026.2.21 before 2026.4.10 contain an authentication bypass vulnerability in the sandbox noVNC helper route that exposes interactive browser session credentials. Attackers can access the noVNC helper route without bridge authentication to gain unauthorized access to the...

CVE-2026-43581

OpenClaw before 2026.4.10 contains an improper network binding vulnerability in the sandbox browser CDP relay that exposes Chrome DevTools Protocol on 0.0.0.0. Attackers can access the DevTools protocol outside intended local sandbox boundaries by exploiting the overly broad binding configuration...