OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.22 contained security vulnerabilities. These vulnerabilities stemmed from incomplete host environment variable cleanup mechanisms in the host-env-security-policy.json and...

OpenClaw 路径遍历漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.8 contained a path traversal vulnerability. This vulnerability stemmed from a bypass of the file system policies during the.docx upload processing, allowing attackers to read...

PT-2026-35776

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.3.31 Description An exec allowlist bypass allows attackers to inherit allowlist trust through shell init-file wrapper invocations. By utilizing shell options such as --rcfile, --init-file, and --startup-file,...

OpenClaw 竞争条件问题漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.4 contained a race-condition vulnerability. This vulnerability stemmed from race conditions in shared key authentication, which could allow concurrent asynchronous requests to...

PT-2026-35795

OpenClaw before 2026.4.4 contains a race condition vulnerability in shared-secret authentication that allows concurrent asynchronous requests to bypass the per-key rate-limit budget. Attackers can exploit this by sending multiple simultaneous authentication attempts to circumvent intended...

OpenClaw 安全漏洞

OpenClaw is an intelligent artificial assistant developed under the OpenClaw open source framework. Versions of OpenClaw prior to 2026.3.28 contained security vulnerabilities. These vulnerabilities were caused by a Webhook replay issue during Plivo V3 signature verification. This issue could allo...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.8 contained security vulnerabilities. These vulnerabilities stemmed from a security bypass issue in node.invokebrowser.proxy, which allowed modification of persistent browser...

PT-2026-35786

OpenClaw before 2026.3.31 misclassifies proxied remote requests as loopback connections in the diffs viewer when allowRemoteViewer is disabled, allowing unauthorized access. Attackers can bypass access controls by sending proxied requests that are incorrectly identified as local loopback traffic,...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.8 contained security vulnerabilities. These vulnerabilities stemmed from the lack of cross-channel permission list writing that is performed only by the owner at the /allowlist...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.28 contained security vulnerabilities. These vulnerabilities stemmed from authorization bypass vulnerabilities in the /phone arm and /phone disarm endpoints, which failed to...

AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents

Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain confined to a single interface; instead, they can propagat...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.28 contained security vulnerabilities. These vulnerabilities stemmed from an execution approval vulnerability in the exec-approvals-allowlist.ts file, which allowed the...

PT-2026-35806

OpenClaw versions before 2026.4.8 fail to enforce integrity verification on downloaded plugin archives. Attackers can install malicious or tampered plugin packages without detection, compromising the local assistant environment...

OpenClaw 路径遍历漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.4.2 contained a path traversal vulnerability. This vulnerability stemmed from a directory deletion vulnerability in the mirror mode, allowing attackers to delete remote directorie...

PT-2026-35804

OpenClaw before 2026.4.8 contains an improper authorization vulnerability where the node.pair.approve method accepts operator.write scope instead of the narrower operator.pairing scope, allowing unprivileged users to approve node pairing. Attackers with operator.write permissions can bypass pairi...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.31 contained a security vulnerability. This vulnerability stemmed from a resource exhaustion issue during media downloads, which could allow attackers to bypass security...

PT-2026-35791

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.3.31 Description A resource exhaustion issue exists in media downloads that bypasses core safety limits regarding file size, count, and cleanup operations. This allows attackers to exhaust disk space by...

PT-2026-35759

OpenClaw before 2026.3.31 performs Discord audio preflight transcription before validating member authorization, allowing unauthenticated attackers to consume resources. Remote attackers can trigger audio preflight processing without member allowlist validation to cause resource exhaustion...

OpenClaw Backlink Vulnerability (CNVD-2026-19028)

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from a backlink vulnerability that can be exploited by an attacker to upload a tar archive file containing a symbolic link to escape the sandbox and overwrite files on a remote host...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.31 contained security vulnerabilities. These vulnerabilities stemmed from incomplete range clearance issues in the trusted proxy authentication mode, which could allow attackers...