A vulnerability in openclaw-cli allows a sandboxed session spawn to expose the real workspace path to child prompts. This occurs when a child session is spawned from a sandboxed parent, potentially revealing the host workspace location or related memory context. The issue affects versions from 2026.1.29 up to but not including 2026.4.26. The vulnerability does not alter the trusted-operator model of OpenClaw. A fix is available in version 2026.4.26. Until patched, users should avoid spawning child sessions from sensitive sandboxed workspaces and apply recommended hardening measures.
OpenClaw CLI versions from 2026.1.29 up to but not including 2026.5.2 have a vulnerability where message.action forwarding can send Gateway credentials to model-supplied loopback URLs. This occurs when model-controlled action metadata selects a loopback Gateway URL, potentially exposing tokens and action payloads to a local listener. The vulnerability depends on the operator's configuration and whether untrusted input can reach this path. A patch is available in version 2026.5.2. Mitigations include restricting message action forwarding, avoiding model-supplied loopback targets until patched, and narrowing allowlists.
A vulnerability in OpenClaw CLI allows native command authorization to bypass owner-only command enforcement. This means that a sender able to trigger native command handling could execute commands reserved for owners without proper authorization. The issue affects versions from 2026.1.29 up to but not including 2026.5.6. The vulnerability does not affect the overall trusted-operator model but depends on specific feature enablement and configuration. A patch is available in version 2026.5.6. Until patched, limiting native command access to trusted senders and narrowing allowlists are recommended mitigations.
OpenClaw CLI versions from 2026.1.29 up to but not including 2026.5.18 have a vulnerability where the exec approval UI truncates long commands, potentially hiding parts of the command that will execute. This can cause an approver to unknowingly approve a command with a hidden suffix that may perform unintended operations. The issue affects deployments with exec approval enabled and authenticated users able to submit long exec requests. The vulnerability does not allow unauthenticated access or change the local trust model. A fix is available in version 2026.5.18.
OpenClaw CLI on POSIX nodes has a vulnerability in its system.run safe-bin allowlist where shell expansion can widen the approved commands, allowing unintended file operands. This affects configurations using safe-bin or allowlist auto-approval with commands that include shell-expanded values. A lower-privilege operator could exploit this to read node-local files not intended by policy, potentially exposing sensitive configuration or local information. The issue is a policy enforcement gap in argument validation, not a general flaw in safe-bin commands. The vulnerability is patched in OpenClaw version 2026.5.18 and later.
OpenClaw CLI versions from 2026.1.29 up to but not including 2026.5.18 have a vulnerability where same-host trusted-proxy deployments could accept locally forged identity headers. This allows a local caller on the same host who can access the proxy-facing Gateway port to supply identity headers normally reserved for the trusted proxy. The vulnerability affects operator identity handling when the feature is enabled and reachable. A patch is available in version 2026.5.18. Mitigations include restricting access to the trusted-proxy ingress behind a proxy and firewall, narrowing allowlists, avoiding sharing Gateways between untrusted users, and disabling the feature if not needed.
A vulnerability in OpenClaw CLI's QQBot streaming command allows mutation of configuration without requiring an explicit allowFrom whitelist entry. This can lead to unauthorized configuration changes when the feature is enabled and accessible. The issue affects versions from 2026.1.29 up to but not including 2026.4.29. A patch is available in version 2026.4.29. Mitigations include disabling the command or restricting it to trusted senders until patched.
A vulnerability in OpenClaw CLI's QQBot pre-dispatch slash commands allows these commands to bypass configured allowFrom policy checks. This means that a QQBot sender with the ability to invoke slash commands could dispatch commands before the policy restricting command sources is applied. The issue affects versions from 2026.1.29 up to but not including 2026.4.27. The vulnerability does not alter the trusted-operator model of OpenClaw, and its impact depends on specific operator configurations and exposure of the affected feature. A fix is available starting with version 2026.4.27.
OpenClaw CLI versions from 2026.1.29 up to but not including 2026.5.12 have a vulnerability where PowerShell encoded-command aliases may bypass execution allowlist checks. This allows encoded PowerShell commands to run without proper allowlist validation if abbreviated alias forms are used. The vulnerability affects configurations where the feature is enabled and reachable, potentially allowing execution of unauthorized encoded PowerShell content. The issue does not alter the trusted-operator model of OpenClaw. A patch is available starting with version 2026.5.12. Until patched, it is recommended to avoid allowlisting PowerShell wrapper forms and require approval for encoded commands. Additional mitigations include narrowing allowlists, avoiding shared Gateways between untrusted users, and disabling the affected feature if not needed.
OpenClaw CLI versions from 2026.1.29 up to but not including 2026.5.6 have a vulnerability where Mattermost event handlers may improperly process events missing channel type metadata, bypassing intended direct message (DM) policy enforcement. This could allow events that should be restricted by channel policy to be processed when the affected feature is enabled. The vulnerability does not affect the overall trusted-operator model of OpenClaw. A patch is available in version 2026.5.6. The CVSS score is 3.7, indicating low severity.
A vulnerability in OpenClaw CLI allows node pairing reconnection to confuse the approval scope state, potentially broadening node authority beyond operator intent. This affects versions from 2026.1.29 up to but not including 2026.5.28. The issue arises when a paired or reconnecting node session mutates pairing state, impacting approval scope decisions. The vulnerability does not alter the trusted-operator model but can present increased authority if the affected feature is enabled and reachable. A fix is available starting with version 2026.5.27. Operators are advised to revoke unexpected node pairings and re-pair only trusted nodes until patched, and to harden configurations by narrowing allowlists and disabling the feature if not needed.
A vulnerability in openclaw-cli allows trusted retry endpoint checks to match hostname prefixes, potentially causing authentication material to be sent to unintended endpoints. This issue affects versions from 2026.1.29 up to but not including 2026.5.7. The vulnerability arises when a retry endpoint URL chosen by lower-trust input passes validation by resembling a trusted host via hostname prefix matching. The impact depends on the operator's configuration and exposure of the affected feature. A patch is available in version 2026.5.7. Until patched, retry endpoints should be pinned to exact trusted origins, and the affected feature should be disabled if not needed.
OpenClaw CLI versions from 2026.1.29 up to but not including 2026.5.12 have a vulnerability where custom headers configured for MCP Streamable HTTP servers may be forwarded to a different origin if the MCP endpoint issues a cross-origin redirect. This can expose sensitive headers such as API keys or tenant-routing headers to unintended recipients. The issue only affects deployments using streamable-http transport with custom headers and MCP endpoints that can redirect cross-origin. A fix is available starting with version 2026.5.12.
OpenClaw CLI versions from 2026.1.29 up to but not including 2026.5.12 export session HTML that may retain unsafe markdown links such as javascript: or data: URLs. This can lead to browser-side script execution if a trusted operator opens the exported file and activates such a link. The vulnerability affects the exported session HTML feature and depends on operator configuration and input trust levels. A fix is available in version 2026.5.12. Users are advised not to open exported session HTML from untrusted content in privileged browser profiles until patched and to limit sharing of Gateways between untrusted users.
A vulnerability in openclaw-cli allows a workspace .env file to influence which Python runtime the gcloud command uses via the CLOUDSDK_PYTHON environment variable. This can affect the Gmail setup process when run by a trusted operator. The issue exists in versions from 2026.1.29 up to but not including 2026.5.2. The vulnerability does not alter the trusted-operator model but could lead to unintended Python execution paths if lower-trust input reaches the affected feature. A fix is available in version 2026.5.2.
A vulnerability in openclaw-cli allows a device with a surviving pairing-scoped session to regain node token authority after that token has been revoked. This undermines the intended revocation mechanism, potentially allowing continued node-level access without renewed approval. The issue affects devices that already had legitimate pairing and session footholds. The vulnerability is patched in openclaw-cli version 2026.5.26 and later.
A vulnerability in OpenClaw CLI's memory-wiki shared search feature allows bypassing session visibility checks, potentially exposing memory entries to unauthorized sessions. This issue affects versions from 2026.1.29 up to but not including 2026.4.29. The vulnerability requires the affected feature to be enabled and reachable, and its impact depends on operator configuration and trust boundaries. A fix is available starting with version 2026.4.29. Until patched, limiting shared memory search to trusted operators and narrowing allowlists are recommended mitigations.
A vulnerability in OpenClaw CLI allows skill-command dispatch to skip before-tool-call hooks, potentially bypassing hook-based auditing or policy enforcement. This affects versions from 2026.1.29 up to but not including 2026.5.6. The issue does not alter the trusted-operator model but may impact security depending on configuration and input trust levels. A patch is available in version 2026.5.6. Users are advised to avoid relying solely on hook enforcement for skill commands until patched and to apply general hardening measures such as restricting allowlists and disabling the affected feature if not needed.
A vulnerability in OpenClaw CLI allows a Gateway caller with operator.write access to mutate global configuration without requiring operator.admin privileges. This issue affects versions from 2026.1.29 up to but not including 2026.5.6. The vulnerability depends on the affected feature being enabled and reachable, and the practical impact varies based on operator configuration and input trust levels. The vendor has released a patch in version 2026.5.6. Until patched, limiting Active Memory write access to trusted operators and narrowing allowlists are recommended mitigations.
OpenClaw CLI versions from 2026.1.29 up to but not including 2026.5.28 have a vulnerability where the exec allowlist may not detect side effects caused by transparent command wrappers. This can lead to unintended wrapper-level side effects executing outside the intended allowlisted command. The issue affects configurations where the vulnerable feature is enabled and reachable. The vulnerability does not alter OpenClaw's trusted-operator model. A fix is available starting with version 2026.5.26. Mitigations include careful review and approval of shell-like wrapper commands, narrowing allowlists, avoiding shared Gateways among untrusted users, and disabling the affected feature if not needed.