OpenClaw (npm package openclaw) before 2026.7.1 incorrectly binds Signal approval reactions. In affected versions, a reaction intended to resolve a structured approval request could instead attach to ordinary outbound text when unrelated outbound messages and a pending approval are present in the same conversation. As a result, an approver's reaction to unrelated text could be interpreted as approving or denying a pending host action; the practical impact depends on the pending request, conversation timing, and the actions available to the OpenClaw process. The issue does not change the authority of correctly identified approvers. This is fixed in version 2026.7.1.

OpenClaw (npm package 'openclaw') before 2026.7.1 is vulnerable to a time-of-check time-of-use race condition in OpenShell local mirror filesystem mutation operations. The remove, mkdir, and rename operations could act on a different filesystem target after OpenClaw completed its sandbox path-safety check, if the path is changed concurrently. An attacker able to win the race can cause a sandboxed operation to delete, create, or rename a host path outside the intended mirror root with the permissions of the OpenClaw process user. This does not require an operator to have granted host filesystem access outside the sandbox. The issue is fixed in 2026.7.1.

OpenClaw is an agent gateway distributed via npm. In versions >= 2026.4.10 and < 2026.7.1, persistent memory dreaming mutations omit owner permission checks. An authorized but non-owner external-channel sender can issue the persistent '/dreaming on' and '/dreaming off' commands to enable or disable the Gateway's Memory Core dreaming behavior, disabling background memory processing or re-enabling durable memory promotion where the owner expected it to remain disabled; the practical confidentiality, integrity, and availability impact depends on stored conversation material and subsequent memory use. Read-only status and help commands remain governed by normal command policy. The issue is fixed in version 2026.7.1. As a workaround, disable dreaming commands in external channels or restrict channel command access to owners.

OpenClaw (npm package openclaw) before 2026.7.1 does not enforce the documented owner-only requirement for persistent /activation policy changes in group channels. An authorized non-owner channel sender can change whether the agent requires mention-based activation, causing the agent to respond more broadly in the group (exposing its responses to additional group traffic) or suppressing expected activation behavior until an owner restores the intended setting. The issue is fixed in version 2026.7.1.

OpenClaw is an npm-distributed agent gateway. In versions before 2026.7.1, the global Active Memory toggle mutations could omit owner checks. An authorized non-owner external-channel sender could therefore persistently enable or disable Active Memory for the Gateway, disabling memory recall for future sessions or re-enabling global recall where the owner expected it to remain disabled. The issue is limited to persistent global on/off mutations; session-level controls and read-only status remain governed by existing command policy. The issue is fixed in version 2026.7.1. (Suggested title: "OpenClaw before 2026.7.1 missing owner authorization check on Active Memory global toggles".)

OpenClaw (npm package 'openclaw') before 2026.7.1 does not enforce the administrator scope requirement on browser control when it is reached through the node.invoke method, although direct browser.request access requires administrator scope. In Gateway deployments that honor caller identity and narrower operator scopes, a write-scoped caller with access to a connected browser-capable node can inspect pages, navigate tabs, or interact with browser-visible applications without the configured admin requirement; practical impact depends on the browser profile and signed-in state. Shared-secret token and password callers are considered fully trusted operators under OpenClaw's security model and are not affected. The issue is fixed in 2026.7.1.

OpenClaw (npm package openclaw) before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel bridge. An authorized non-owner channel sender with channel command access can approve or deny a pending permission request intended for the owner, causing the requested action to proceed without owner consent. The practical impact depends on the pending action and the host capabilities requested by the Claude Code run. The issue is fixed in version 2026.7.1.

OpenClaw is an npm-distributed agent runtime. In versions >= 2026.2.26 and < 2026.7.1, PowerShell command analysis on Windows hosts running in exec allowlist mode could approve an exact executable resolved from PATH but subsequently execute a same-named executable located in the workspace directory. If lower-trust content can place an executable with an approved basename into an agent-writable workspace and steer an approved PowerShell command that uses a bare executable name, OpenClaw may run the workspace file instead of the allowlisted path, executing arbitrary code with the privileges of the Gateway or node-host user. The issue does not require replacement of the approved executable itself. Version 2026.7.1 contains a fix; as a workaround, avoid bare executable names in approved PowerShell commands and keep executable files out of agent-writable workspaces.

OpenClaw (npm package 'openclaw') before 2026.7.1 improperly handles case sensitivity in the model-facing cron tool: a mixed-case payload kind can pass the agent-facing shell-execution guard and later normalize into a command job. An actor able to steer a tool-enabled agent can therefore create a persistent cron job that executes attacker-selected commands with the privileges of the OpenClaw process user, resulting in access to host files and credentials and impact to scheduled service availability. The issue is limited to cron jobs created or edited through the model-facing cron tool; direct CLI and authorized Gateway scheduling surfaces are trusted operator controls. Fixed in 2026.7.1.

OpenClaw (npm package 'openclaw') before 2026.7.1 incorrectly trusts requester provenance in message.action. In identity-bearing Gateway deployments (authentication modes that honor caller identity and narrower operator scopes), a write-scoped caller can supply another sender's identifier to the channel authorization checks and invoke a channel action under that spoofed requester identity, reaching operations the channel adapter would have denied to the real caller. Practical impact depends on the enabled channel, the action, and the target account's permissions. Shared-secret token and password callers are full trusted operators under OpenClaw's security model and are out of scope. The issue is fixed in 2026.7.1; as a workaround, restrict message.action to administrators and disable sensitive channel actions that rely on requester identity.

OpenClaw (npm package openclaw) before 2026.7.1 fails to restrict owner-only infrastructure tools exposed through the chat.send endpoint. In Gateway deployments using authentication modes that honor caller identity and narrower operator scopes, a write-scoped non-owner caller can start a chat turn whose tool inventory includes the gateway and cron tools, causing the agent to invoke owner-only configuration or scheduling operations, including persistent state changes. Practical impact depends on the tools selected by the model and the caller's ability to steer the turn. Shared-secret token and password callers are treated as fully trusted operators under OpenClaw's security model and are outside the scope of this issue. The issue is fixed in 2026.7.1; as a workaround, restrict chat.send to administrators in identity-bearing deployments and remove gateway and cron from affected agent tool policies.

OpenClaw (npm package 'openclaw') before 2026.8.1 contains a server-side request forgery vulnerability in its trusted-host DNS checks. For fetches that use the trusted-host DNS recheck, a trusted hostname that resolves to an unspecified address (0.0.0.0 or ::) bypasses the SSRF destination validation. An attacker who can influence DNS for an allowed hostname can therefore cause a guarded fetch to reach a service bound only to loopback and disclose its response; the practical impact depends on the reachable service and the data it returns. Fixed in 2026.8.1.

OpenClaw (npm package 'openclaw') versions >= 2026.6.6 and < 2026.8.1 apply the SMS webhook invalid-request rate limit before Twilio signature verification and identify clients only by the raw proxy socket address. In deployments where the SMS/Twilio webhook sits behind a trusted reverse proxy or tunnel so that multiple external clients share one socket address, an unauthenticated remote sender can exhaust the shared pre-authentication rate-limit budget with invalid requests, causing subsequent correctly signed Twilio callbacks to receive HTTP 429 responses. The result is temporary inbound SMS loss while the shared window remains exhausted; the attacker cannot forge a callback or access message data. Fixed in 2026.8.1.

OpenClaw (npm package 'openclaw') versions >= 2026.3.28 and < 2026.8.1 allow an untrusted workspace .env file to set the CLOUDSDKPYTHONARGS environment variable. When an operator starts OpenClaw in attacker-controlled workspace content and then runs the Gmail setup flow, that value is inherited when gcloud is launched, and the gcloud launcher passes it as arguments to the trusted Python interpreter. A crafted CLOUDSDKPYTHONARGS value can therefore cause Python to execute attacker-supplied code with the OpenClaw host user's permissions, allowing credentials to be read, files to be modified, or other processes to be started. This issue is fixed in version 2026.8.1; as a workaround, run Gmail setup only from trusted workspaces and clear inherited CLOUDSDK variables beforehand.

OpenClaw is an npm-distributed application. In versions >= 2026.4.25 and < 2026.8.1, the workspace environment-variable filter did not block variables ending in ENDPOINT, so an untrusted workspace .env file could set AZURESPEECHENDPOINT. Azure Speech preferred that value over the configured region, so when a synthesis or voice-list request was made, the attacker-selected endpoint received the operator's Azure Speech key in the request header, allowing the key to be reused against the operator's Azure Speech resource. Exploitation requires an operator to start OpenClaw in attacker-controlled workspace content with Azure Speech configured with a key and region and no trusted endpoint override set. The issue is fixed in 2026.8.1.

OpenClaw is an agent gateway distributed as the npm package 'openclaw'. In versions >= 2026.4.5 and < 2026.8.1, the Gateway validated a single DNS resolution result for a configured remote Chrome DevTools Protocol (CDP) hostname, but the raw WebSocket and Playwright transports performed a later, independent DNS resolution, discarding the DNS pinning enforced at validation time. An attacker who controls an approved CDP hostname or its DNS answers can exploit this check-then-use gap via DNS rebinding to make the Gateway connect to a loopback, private, link-local, cloud metadata, or other SSRF-policy-denied address. The impact depends on the remote CDP configuration, DNS timing, and the services reachable from the Gateway host. The issue is fixed in 2026.8.1; as a mitigation, disable hostname-based remote CDP endpoints or restrict them to trusted, stable infrastructure.

OpenClaw (npm package openclaw) before 2026.8.1 does not neutralize leading characters that spreadsheet applications interpret as formulas when the Control UI exports session data to CSV. Although session labels were quoted as CSV text, a lower-trust participant who can influence a session label or the first user message can place a formula-like cell in the Usage export; if an operator opens that export in a spreadsheet application with formula evaluation enabled, the cell may be evaluated with the permissions of the spreadsheet user. OpenClaw itself does not evaluate the formula, and practical impact depends on the spreadsheet application's security settings. The issue is fixed in 2026.8.1.

OpenClaw (npm package 'openclaw') versions >= 2026.3.22 and < 2026.8.1 contain an approval-bypass flaw in the exec approval policy: the policy could trust a command-running wrapper without inspecting the command carried in its arguments. After an operator allowlisted or permanently approved a benign wrapper invocation, a later agent turn could substitute an arbitrary inner command and execute it with the OpenClaw process's host privileges without a further approval prompt. Exploitation requires the relevant wrapper to resolve on the host and a prior operator decision allowing that wrapper. Transparent shell carriers and opaque utilities such as process monitors, tracers, namespace tools, and proxy wrappers were affected through related trust-resolution gaps. Fixed in 2026.8.1.

OpenClaw (npm package openclaw) versions >= 2026.5.2 and < 2026.8.1 contain an incorrect authorization vulnerability in WhatsApp group handling. A group sender who is admitted for ordinary messages but denied by commands.allowFrom or owner command authorization can issue the /new <model> command to reset the shared group session and persist a provider and model override. This allows a command-denied group member to select a provider and model already permitted by the operator for subsequent turns in the shared group session, potentially changing provider routing, cost, data flow, or availability. It does not allow adding a new provider or host command execution. The issue is fixed in version 2026.8.1.

OpenClaw is an npm-distributed gateway application. In versions >= 2026.7.1 and < 2026.8.1, Synology Chat attachment delivery could lose DNS pinning: the Gateway validated a single DNS result for a supplied file URL but then passed the original hostname to the Synology NAS, where it could resolve to a different destination. When attachment delivery accepted a remotely influenced hostname, an attacker could use DNS rebinding to make the NAS fetch a private or otherwise policy-denied resource and return its contents to the addressed conversation (server-side request forgery). Practical impact depends on NAS routing, resolver behavior, and the response available at the private destination. The issue is fixed in 2026.8.1; as a workaround, disable remote URL attachment forwarding in Synology Chat.

OpenClaw (npm package 'openclaw') versions >= 2026.5.12 and < 2026.8.1 do not immediately invalidate Canvas HTTP authorization when a paired node is revoked. Node revocation invalidates the WebSocket client, but Canvas HTTP authorization continues to accept and renew the previously granted capability until WebSocket close cleanup completes. As a result, a revoked paired node can continue exercising its Canvas capability against the capability's configured routes during the close grace period. The issue is fixed in 2026.8.1; as a workaround, restart the Gateway after revoking a node that has Canvas access.

OpenClaw (npm package 'openclaw') before 2026.8.1 does not correctly enforce per-chat tool policies for Codex app-server runtime tools. A conversation-level tools.allow rule filtered OpenClaw tools but did not restrict the shell, process, file, and patch tools owned by the Codex runtime. When a lower-trust conversation was assigned to a Codex runtime and restricted with a per-chat tool allowlist, a participant able to trigger that agent could still reach native command and file tools, bypassing the configured allowlist. The practical impact depends on the runtime's host permissions and sandbox configuration. The issue is fixed in 2026.8.1.

OpenClaw (npm package 'openclaw') before 2026.8.1 contains an access-control bypass in the Microsoft Teams integration. When groupPolicy is set to allowlist, a missing or unsupported configured access group produces a denied group-resolution result that is not rejected by the final message-admission check, so a Teams member who is not on the allowlist can still trigger the configured agent despite the administrator's group boundary. The impact depends on the conversations, tools, and data available to that agent. The issue is fixed in version 2026.8.1.

OpenClaw (npm package 'openclaw') versions >= 2026.3.28 and < 2026.8.1 contain a credential exposure issue in memory embedding failover. When remote embedding fallback is configured and the primary embedding provider fails, the request can be sent to a different fallback provider while still reusing the primary provider's configured API key, causing that credential to be transmitted as a bearer token to an unintended vendor. The practical impact depends on the configured providers, whether failover occurs, and the privileges attached to the primary provider key. The issue is fixed in 2026.8.1; as a workaround, disable cross-provider embedding fallback or configure each provider with separate, narrowly scoped credentials.

OpenClaw is a coding agent distributed as the npm package openclaw. In affected versions (2026.7.1 through 2026.7.2), alternate but valid file: URL spellings supplied over the Agent Client Protocol (ACP) were treated as relative paths and were incorrectly classified as reads scoped to the session working directory. When an operator connected openclaw acp client to an untrusted or compromised ACP peer, that peer could request a read of a file outside the session working directory without the approval prompt normally required for that path, resulting in disclosure of local file contents. The demonstrated impact is limited to file confidentiality; mutating and command-capable tool classes are not affected. This issue is fixed in OpenClaw 2026.8.1.

OpenClaw (npm package openclaw) versions >= 2026.7.2 and < 2026.9.2 contain a race condition in the Discord realtime voice transcript path. Concurrent control-classified voice transcripts could consume speaker context belonging to another participant after an asynchronous control check, causing a transcript to inherit another speaker's owner status. In Discord agent-proxy voice sessions using the affected realtime control path, an utterance from a non-owner participant could reach the downstream agent boundary marked as owner, so owner-sensitive behavior is applied to the wrong speaker. Exploitation depends on concurrent transcript timing and on the tools and commands available to the affected agent. The issue is fixed in 2026.9.2; as a workaround, disable Discord realtime voice for agents that distinguish owner and non-owner senders.

OpenClaw (npm package openclaw) before 2026.8.1 incorrectly enforces sender tool policies during session-memory filename generation. In affected versions, filename generation created an embedded helper that retained tools which the originating sender's policy had removed. When session-memory filename generation was enabled for an agent reachable by lower-trust senders, model-mediated instructions could cause the helper to invoke tools outside that sender's effective policy; the demonstrated impact was the creation of persistent scheduled work. Exploitability depends on the model acting on the injected instruction and on which tools the helper exposes. The issue is fixed in 2026.8.1; as a workaround, disable session-memory filename generation for agents reachable by lower-trust senders.

OpenClaw (npm package openclaw) before 2026.8.1 could include deterministic hashes computed over the original, unredacted configuration in redacted configuration responses. When the Gateway password had low entropy and the remaining configuration values were reconstructable, these hashes acted as offline password verifiers: a caller able to obtain the redacted configuration (for example via config.get) could test password candidates offline without going through the rate-limited Gateway authentication path. Recovering the password could grant the documented shared-secret operator authority. Secret references were not affected in the same way. The issue is fixed in 2026.8.1.

OpenClaw (npm package 'openclaw') versions >= 2026.5.28 and < 2026.8.1 mishandle archive listings in the tar.bz2 skill installer: bounded command-output suffixes were treated as complete listings of the archive. A crafted .tar.bz2/.tbz2 skill archive can push prohibited entries out of both retained listings so that entry-count and size checks pass, and the archive is then extracted in full. If an operator approves installation of such a malicious or compromised skill archive, over-limit files or entry counts are persisted in the skill tools directory, consuming disk space or inodes. The issue bypasses OpenClaw's extraction budgets but does not by itself execute archive contents. Fixed in 2026.8.1.

OpenClaw (npm package 'openclaw') before 2026.8.1 does not apply the originating sender's global or per-agent toolsBySender policy when handling outbound attachments. A sender that has been explicitly denied filesystem read tools can still cause a known local file to be read and returned via a final-response media directive or a message attachment, disclosing local file contents to an admitted requester whose agent turn did not include the read tool. Exploitation requires knowledge or derivation of a useful host path and a delivery flow that accepts local attachments. The issue is fixed in version 2026.8.1.