PT-2026-44898

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.5.18 Description A scope bypass exists in the Gateway 'chat.send' endpoint. This issue allows clients with the operator.write scope to execute privileged commands by utilizing inherited external routes. This...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.5.12 contained security vulnerabilities. These vulnerabilities stemmed from a permission escalation flaw in Slack plugin approval processes, allowing authorized users with exec...

PT-2026-44891

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.5.4 Description An authorization bypass exists in the bundled device-pair plugin. This issue allows non-owner authorized chat senders to issue device-pairing bootstrap codes because the system fails to perform...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.29 contained security vulnerabilities. These vulnerabilities stemmed from SSRF policy bypasses in browser debugging and route exports, allowing for the reuse of already opened...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.5.4 contained security vulnerabilities. These vulnerabilities stemmed from authorization bypass vulnerabilities in the bundled device-pair plugin, allowing unauthorized chatters t...

PT-2026-55398

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mgq6-vr84-7m2j. This link is maintained to preserve external references. Original Description OpenClaw before 2026.5.18 contains an authorization bypass vulnerability in QQBot native approval buttons that fails ...

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 a range-bypass vulnerability in the Gateway chat.send route, allowing clients with restricted ranges to...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.29 contained security vulnerabilities. These vulnerabilities stemmed from a strategy-bypass vulnerability in QQBot administrator commands, which allowed authenticated senders to...

PT-2026-44896

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.5.18 Description An authorization bypass exists in the QQBot native approval buttons. The button callback path fails to enforce the configured approver identity, allowing users who are not authorized approvers t...

PT-2026-44892

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...

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 an authorization bypass vulnerability in the QQBot’s native approval button, which failed to enforce th...

PT-2026-44895

OpenClaw before 2026.4.29 contains a policy bypass vulnerability in QQBot admin commands that allows authenticated senders to skip DM-only and allowFrom policy checks. Attackers can route admin commands from unauthorized senders or contexts to execute restricted behavior that policy should have...

PT-2026-44897

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-2026-42437

OpenClaw versions 2026.4.9 before 2026.4.10 contain a denial of service vulnerability in the voice-call realtime WebSocket path that accepts oversized frames without proper validation. Remote attackers can send oversized WebSocket frames to cause service unavailability for deployments exposing th...

CVE-2026-44992

OpenClaw versions 2026.4.5 before 2026.4.20 contain an environment variable injection vulnerability allowing workspace dotenv to override MINIMAXAPIHOST. Attackers can redirect credentialed MiniMax API requests to attacker-controlled origins, exposing the MiniMax API key in Authorization headers...

CVE-2026-43568

OpenClaw versions 2026.4.5 before 2026.4.10 contain a privilege escalation vulnerability allowing write-scoped operators to modify persistent memory dreaming settings. Attackers with write-scoped gateway access can toggle admin-class configuration mutations through the /dreaming endpoint to...

Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures

The rapid evolution of large language model LLM-driven autonomous agents has given rise to OpenClaw, a new class of open-source agent frameworks that operate as continuously running, skill-augmented systems with persistent memory, multi-channel interaction, and high degrees of autonomy. Such...

Denial Of Service (DoS)

OpenClaw is vulnerable to a Denial Of Service DoS. The vulnerability is due to improper validation of oversized frames in the voice-call realtime WebSocket path, which allows a remote attacker to send oversized WebSocket frames and cause service unavailability...

Security, Privacy, and Ethical Risks in OpenClaw

This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While OpenClaw shows strong potential for personal assistance,...

Malicious code in fastgrc-openclaw (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 158457237168ef50e3a6c4cd33f51e23f6aec642593745a3d11b9b4870ef36ce The package is an AI agent policy-check plugin. When a consumer does not configure their own API key, resolveApiKey returns a hardcoded BUNDLEDAPIKEY...