A vulnerability in the openclaw CLI package affects Microsoft Teams SSO invoke handler, which missed sender authorization checks. This flaw allows processing of SSO signin invokes from senders without applying the usual allowlist checks. Versions from 2026.4.10 up to but not including 2026.4.14 are affected. The issue was fixed in version 2026.4.14 by routing SSO invoke handling through the proper Teams sender authorization path and adding coverage for denied senders. Users should upgrade to version 2026.4.14 or later to remediate this vulnerability.
A vulnerability in the openclaw-cli package versions from 2026.2.21 up to but not including 2026.4.10 allows unauthenticated access to the sandbox noVNC helper route, exposing interactive browser session credentials. This issue was fixed in version 2026.4.10 by requiring bridge authentication for access to this route.
Openclaw CLI versions before 2026.4.5 have a vulnerability where the Chrome DevTools Protocol (CDP) /json/version WebSocket URL can redirect to untrusted hosts, allowing a second-hop SSRF-style pivot. This could cause a browser profile to trust a malicious WebSocket URL pointing to a different host. The issue is fixed in version 2026.4.5 and later.
OpenClaw CLI versions before 2026.4.9 contain a vulnerability where browser interaction routes can pivot into the local Chrome DevTools Protocol (CDP) origin, allowing unauthorized creation or reading of local file:// pages despite navigation guards. This issue was fixed in version 2026.4.9 and later.
A vulnerability in openclaw-cli versions 2026.3.31 up to but not including 2026.4.10 allows local async execution completion events to be missed by the heartbeat owner downgrade detection. This can result in a process continuing to run with higher privileges than intended after processing untrusted completion content. The issue is fixed in version 2026.4.10 and later.
A vulnerability in the Openclaw CLI Nostr plugin allowed profile mutation routes to persist profile configuration without requiring admin authority. This issue affects versions prior to 2026.4.10 and was fixed by enforcing the operator.admin scope for these routes. Users should upgrade to version 2026.4.10 or later to mitigate this vulnerability.
OpenClaw CLI versions before 2026.4.10 have a vulnerability where certain browser press/type interaction routes lack complete navigation guard coverage. This flaw allows some interactions to trigger navigation without fully enforcing the server-side request forgery (SSRF) policy. The issue was fixed in version 2026.4.10 and later.
OpenClaw CLI versions prior to 2026.4.10 contain a vulnerability where browser SSRF hostname validation can be bypassed via DNS rebinding. This allows the browser navigation policy to incorrectly validate hostnames or IP addresses, potentially enabling SSRF pivots. The issue was fixed in version 2026.4.10 and later.
A vulnerability in openclaw-cli versions 2026.4.10 through 2026.4.13 allows delivery queue recovery to lose group tool-policy context for media replay. This can cause recovered outbound media to be replayed without enforcing the original session's group tool policy, weakening channel media restrictions after a restart or recovery. The issue is fixed in version 2026.4.14.
A vulnerability in openclaw-cli versions before 2026.4.10 allows operator-supplied environment variables related to interpreter startup to bypass the exec environment denylist. This can influence downstream execution or network behavior. The issue is fixed in version 2026.4.10 and later.
OpenClaw CLI versions prior to 2026.4.15 have a vulnerability where the gateway HTTP and WebSocket handlers cache bearer token authentication at startup. After a SecretRef rotation intended to revoke old tokens, the gateway could continue accepting the old bearer token until the process is restarted. This allows an old token to remain valid longer than intended, posing a high security risk. The issue is fixed in version 2026.4.15 by re-resolving bearer authentication from the current runtime secret snapshot on each request and WebSocket upgrade.
OpenClaw CLI versions prior to 2026.4.15 have a critical vulnerability in Feishu webhook and card-action validation. The vulnerability allows unauthenticated webhook or card-action traffic to reach command dispatch due to fail-open validation paths when the encryptKey configuration is missing or when blank card-action callback tokens are accepted. The issue is fixed in version 2026.4.15, which enforces fail-closed validation, rejects invalid signatures, and refuses to start webhook mode without an encryptKey.
A vulnerability in OpenClaw CLI's QMD backend allowed reading arbitrary Markdown files within the workspace root, bypassing intended memory-path restrictions. This issue affected versions prior to 2026.4.15 and was fixed in that release by restricting reads to canonical or indexed QMD workspace paths only. Exploitation requires access to the memory tool interface and is limited to workspace Markdown files, resulting in a low severity impact.
Openclaw CLI versions up to 2026.4.21 contain a vulnerability where OpenShell filesystem bridge writes can be redirected outside the sandbox mount root due to a time-of-check/time-of-use (TOCTOU) race condition involving symlink swaps. This could allow unauthorized modification of files outside the intended sandbox. The issue is fixed in version 2026.4.22 by validating write paths against the mount root and rejecting unsafe symlinks.
CVE-2026-44113 is a medium severity vulnerability in the openclaw npm package (openclaw-cli) affecting versions from 2026.1.29 up to but not including 2026.4.22. It involves a time-of-check/time-of-use (TOCTOU) race condition in the OpenShell sandbox filesystem reads, where a symlink swap could allow reading bytes outside the intended mount root. The issue is fixed in version 2026.4.22 by enforcing no-follow semantics on file opens, validating file descriptors against the canonical mount root, rejecting unsafe hardlink/symlink cases, and using strict ancestor walks on platforms lacking fd-path readback. The fix is publicly available and verified in the npm package.
OpenClaw CLI versions before 2026.4.20 have a vulnerability where workspace .env files can override runtime-control environment variables prefixed with OPENCLAW_. This allows a malicious workspace to influence trusted OpenClaw runtime behavior by setting variables like OPENCLAW_GIT_DIR. The issue requires running OpenClaw from an attacker-controlled workspace. The vulnerability is rated with a CVSS score of 7.8 (high severity) and has been fixed in version 2026.4.20 by reserving the OPENCLAW_ namespace and rejecting conflicting dotenv entries.
OpenClaw CLI versions up to 2026.4.21 have a vulnerability where the exec allowlist analysis fails to reject shell expansions in unquoted heredocs. This flaw allows an approved command to appear safe while the shell evaluates potentially unsafe expansions at runtime. The issue is fixed in version 2026.4.22 by enhancing the exec command analyzer to properly track heredoc bodies and reject unquoted expansions.
OpenClaw CLI versions before 2026.4.20 contain a vulnerability in the QQBot direct media upload feature where attacker-controlled image URLs bypass SSRF validation. This flaw allows unintended forwarding of media delivery request URLs, but it is limited to outbound QQBot media handling and does not expose arbitrary local files. The issue is rated as medium severity and has been fixed in version 2026.4.20.
A vulnerability in openclaw-cli versions up to 2026.4.21 allows a non-owner loopback client to spoof owner context metadata via request headers. This could enable unauthorized access to owner-gated operations. The issue is fixed in version 2026.4.22 by issuing separate bearer tokens for owner and non-owner contexts and no longer trusting the spoofable sender-owner header.
OpenClaw CLI versions up to 2026.4.20 have a vulnerability where owner-enforced slash commands could be executed by non-owner senders if the channel plugin allowed wildcard inbound senders and no explicit owner allowance was configured. This flaw affects the authorization logic for commands such as /send, /config, and /debug, potentially allowing unauthorized command execution on affected channels. The issue does not grant broader administrative or host access. The vulnerability is fixed in version 2026.4.21.