CVE-2026-53809 OpenClaw < 2026.4.25 - Provider Alias Confusion in Embedded Runner Policy

OpenClaw before 2026.4.25 contains a policy bypass vulnerability in embedded runner policy that allows requests using provider aliases to compare against aliases instead of canonical provider identities. Attackers can exploit this confusion to select bundled tool access outside intended provider...

CVE-2026-53809 OpenClaw < 2026.4.25 - Provider Alias Confusion in Embedded Runner Policy

OpenClaw before 2026.4.25 contains a policy bypass vulnerability in embedded runner policy that allows requests using provider aliases to compare against aliases instead of canonical provider identities. Attackers can exploit this confusion to select bundled tool access outside intended provider...

CVE-2026-53808

OpenClaw prior to 2026.5.6 contains an approval policy bypass in the Skill Workshop apply flow, allowing attacker-controlled agent tool calls to set apply: true despite approvalPolicy: pending. This enables modification of workshop configurations without proper authorization when the affected app...

CVE-2026-53808 OpenClaw < 2026.5.6 - Approval Policy Bypass in Skill Workshop Apply Flow

OpenClaw before 2026.5.6 contains an approval policy bypass vulnerability in the Skill Workshop apply flow that allows agent tool calls to set apply: true despite approvalPolicy: pending configuration. Attackers can exploit this by reaching the affected apply path to apply workshop changes before...

EUVD-2026-36314

OpenClaw before 2026.5.6 contains an approval policy bypass vulnerability in the Skill Workshop apply flow that allows agent tool calls to set apply: true despite approvalPolicy: pending configuration. Attackers can exploit this by reaching the affected apply path to apply workshop changes before...

CVE-2026-53808 OpenClaw < 2026.5.6 - Approval Policy Bypass in Skill Workshop Apply Flow

OpenClaw before 2026.5.6 contains an approval policy bypass vulnerability in the Skill Workshop apply flow that allows agent tool calls to set apply: true despite approvalPolicy: pending configuration. Attackers can exploit this by reaching the affected apply path to apply workshop changes before...

CVE-2026-53808 OpenClaw < 2026.5.6 - Approval Policy Bypass in Skill Workshop Apply Flow

OpenClaw before 2026.5.6 contains an approval policy bypass vulnerability in the Skill Workshop apply flow that allows agent tool calls to set apply: true despite approvalPolicy: pending configuration. Attackers can exploit this by reaching the affected apply path to apply workshop changes before...

CVE-2026-53807 OpenClaw < 2026.5.6 - Authorization Bypass in Telegram Interactive Callbacks via commands.allowFrom

OpenClaw before 2026.5.6 contains an authorization bypass vulnerability in Telegram interactive callbacks that allows authenticated users to skip commands.allowFrom validation. Attackers can invoke affected callbacks to mark themselves as authorized senders before allowlist checks are applied,...

CVE-2026-53807 OpenClaw < 2026.5.6 - Authorization Bypass in Telegram Interactive Callbacks via commands.allowFrom

OpenClaw before 2026.5.6 contains an authorization bypass vulnerability in Telegram interactive callbacks that allows authenticated users to skip commands.allowFrom validation. Attackers can invoke affected callbacks to mark themselves as authorized senders before allowlist checks are applied,...

CVE-2026-53807 OpenClaw < 2026.5.6 - Authorization Bypass in Telegram Interactive Callbacks via commands.allowFrom

OpenClaw before 2026.5.6 contains an authorization bypass vulnerability in Telegram interactive callbacks that allows authenticated users to skip commands.allowFrom validation. Attackers can invoke affected callbacks to mark themselves as authorized senders before allowlist checks are applied,...

EUVD-2026-36313

OpenClaw before 2026.5.6 contains an authorization bypass vulnerability in Telegram interactive callbacks that allows authenticated users to skip commands.allowFrom validation. Attackers can invoke affected callbacks to mark themselves as authorized senders before allowlist checks are applied,...

CVE-2026-53807

OpenClaw prior to 2026.5.6 is vulnerable to an authorization bypass in Telegram interactive callbacks via commands.allowFrom. An authenticated user can invoke affected callbacks to bypass allowlist validation and mark themselves as authorized senders, enabling command behavior outside Telegram se...

CVE-2026-53806 OpenClaw < 2026.5.12 - Shell Option Parsing Bypass in Exec Revalidation

OpenClaw before 2026.5.12 contains a shell option parsing vulnerability that allows combined POSIX shell flags to bypass exec revalidation checks. Attackers can exploit this by using combined shell options to execute inline shell content without intended allowlist validation, potentially enabling...

CVE-2026-53806 OpenClaw < 2026.5.12 - Shell Option Parsing Bypass in Exec Revalidation

OpenClaw before 2026.5.12 contains a shell option parsing vulnerability that allows combined POSIX shell flags to bypass exec revalidation checks. Attackers can exploit this by using combined shell options to execute inline shell content without intended allowlist validation, potentially enabling...

CVE-2026-53806 OpenClaw < 2026.5.12 - Shell Option Parsing Bypass in Exec Revalidation

OpenClaw before 2026.5.12 contains a shell option parsing vulnerability that allows combined POSIX shell flags to bypass exec revalidation checks. Attackers can exploit this by using combined shell options to execute inline shell content without intended allowlist validation, potentially enabling...

CVE-2026-53806

OpenClaw vulnerability CVE-2026-53806 affects OpenClaw prior to version 2026.5.12. A shell option parsing flaw allows combined POSIX shell flags to bypass exec revalidation checks, enabling execution of inline shell content without the intended allowlist validation when the affected feature is en...

New Attacks Trick OpenClaw AI Agent Into Running Code and Leaking Secrets

Two security teams have shown, in separate research published this week, that OpenClaw, the popular self-hosted AI agent, can be driven to run attacker-controlled code or hand over sensitive data through ordinary-looking inputs. Imperva buried instructions inside shared contacts, vCards, and...

PT-2026-48745

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.5.19 Description An authorization bypass exists in message read actions due to insufficient validation, which allows the system to skip channel allowlist checks. This enables lower-trust callers to request and...

PT-2026-48738

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.5.6 Description An approval policy bypass exists in the Skill Workshop apply flow. This issue allows agent tool calls to set the apply variable to true even when the approvalPolicy is configured as pending. An...

OpenClaw 权限许可和访问控制问题漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.5.27 had code-related vulnerabilities. These vulnerabilities stemmed from issues with code execution during the skill installation process. The workarea.env file could override th...