OpenClaw CLI versions prior to 2026.2.13 log certain WebSocket request headers without sanitization or length limits when connections close before completing the handshake. This can allow unauthenticated clients to inject crafted header values into logs. If these logs are later processed by AI-assisted debugging tools or LLMs, this may lead to indirect prompt injection (log poisoning). The issue is fixed in version 2026.2.13 by sanitizing and truncating header values before logging.
OpenClaw CLI versions up to 2026.2.25 have a vulnerability in the voice-call Twilio webhook path where replay detection could be bypassed by manipulating an unsigned idempotency header. This allowed replayed webhook events to be accepted as fresh events. The issue is fixed in version 2026.2.26 by binding replay deduplication to authenticated request identity rather than mutable unsigned headers.
OpenClaw CLI versions up to 2026.4.2 have a vulnerability where lower-trust background runtime output is incorrectly injected into trusted System events. This flaw allows potentially untrusted output to be promoted to trusted status, enabling prompt injection into subsequent agent operations. The issue affects the OpenClaw trust model in a local assistant context and does not involve multi-tenant service boundaries. A patch is available in version 2026.4.8.
A vulnerability in the openclaw CLI package causes a mismatch in authorization scope for LINE group allowlists. Sender IDs approved via direct message (DM) pairing could improperly satisfy group allowlist checks, allowing broader group sender access than intended. This is due to group allowlist composition inheriting entries from the DM pairing store. The issue affects versions up to 2026.2.25 and is fixed starting from version 2026.2.26.
OpenClaw CLI versions up to 2026.2.23 have a vulnerability where inbound media in Telegram direct messages is downloaded and written to disk before sender authorization checks are completed. This allows unauthorized senders to trigger media download and disk write operations even when direct message access should be denied. The issue affects versions from 2026.1.29 up to but not including 2026.2.24. The vulnerability is fixed in version 2026.2.24, which enforces authorization before media handling.
OpenClaw CLI versions up to 2026.2.24 have an SSRF IP classification bypass where IPv6 multicast addresses (ff00::/8) were not treated as blocked or private. This allowed these multicast addresses to pass SSRF preflight checks. The issue was addressed in version 2026.2.25. The vulnerability is considered low severity as it is a defense-in-depth hardening issue and network fetches are limited to HTTP/HTTPS.
A vulnerability in the openclaw CLI allows a gateway client with operator.write privileges to perform persistent configuration changes via the chat.send command interface, which was intended to be restricted to operator.admin users. This issue arises from an authorization mismatch in the handling of /config set and /config unset commands routed through chat.send. The vulnerability was patched in version 2026.3.7. Exploitation requires an authenticated gateway client with specific permissions and enabled command support. The severity is rated medium due to the scoped nature of the privilege escalation and the requirement for prior authentication.
OpenClaw CLI versions from 2.0.0-beta3 up to but not including 2026.2.12 have a vulnerability where the POST /hooks/agent endpoint accepts an externally supplied sessionKey for routing messages. This allows an authenticated hook token holder to inject messages into targeted sessions by overriding session keys. The vulnerability impacts message integrity and can persist poisoned context in sessions. Confidentiality impact is secondary and depends on other weaknesses. The issue is fixed in version 2026.2.12 by restricting sessionKey acceptance and adding configuration options to control session routing securely.
The openclaw npm package prior to version 2026.2.25 contains a vulnerability in the MS Teams file-consent flow where pending uploads could be completed or canceled across different conversations due to missing conversation binding verification. This allows an attacker with a valid uploadId to manipulate pending uploads in other conversations. The issue is fixed in version 2026.2.25 by enforcing conversation ID matching before processing upload acceptance or cancellation.
OpenClaw CLI versions up to 2026.3.2 contain a vulnerability in the system.run environment override sanitization that allows dangerous environment variable overrides to bypass allowlist and approval mechanisms. This enables an attacker with existing system.run invocation rights to influence subprocess behavior via environment variables like GIT_SSH_COMMAND and GIT_CONFIG_*, causing helper-command execution or config loading outside the reviewed command semantics. The issue is fixed in version 2026.3.7.
OpenClaw CLI versions up to 2026.4.2 contain a vulnerability where authenticated `/hooks/wake` and mapped `wake` payloads are incorrectly promoted into the trusted `System:` prompt channel instead of being treated as untrusted events. This issue affects the OpenClaw trust model in a local user-controlled context and does not assume multi-tenant service boundaries. The vulnerability has been fixed in version 2026.4.8.
OpenClaw CLI is vulnerable to local file exfiltration via injection of MEDIA: directives in MCP tool result content. A malicious or compromised MCP tool server can specify arbitrary file paths within allowed directories such as the OS temporary directory, causing OpenClaw to read and send those files to external messaging channels like Discord, Slack, Telegram, and WhatsApp without user awareness. This vulnerability affects all OpenClaw versions up to and including 2026.7.1. The flaw arises from unvalidated extraction of MEDIA: tokens, an overly broad default allowlist including os.tmpdir(), and delivery of file contents to external channels. Secondary attack vectors include fallback on image content paths and support for file:// URI schemes. The impact includes theft of sensitive temporary files and silent exfiltration to attacker-controlled channels. A patch is available to remediate this issue.
A path traversal vulnerability in the OpenClaw CLI ZIP extraction logic allowed writes outside the intended extraction directory when a pre-existing symlink was present in the destination path. This could lead to arbitrary file writes outside the extraction root. The issue affects openclaw versions up to and including 2026.2.21-2 and is fixed in version 2026.2.22. The vulnerability requires attacker-controlled archive extraction and a pre-existing symlink in the destination path.
OpenClaw CLI has an authentication inconsistency in its local Chrome extension relay feature. The /extension WebSocket endpoint accepts unauthenticated connections on the local loopback interface, while other relay endpoints require authentication. This allows a local process on the same machine to connect without a token and interfere with extension-relay behavior. No remote exploitation is possible. A fix is available that enforces token authentication on all relay endpoints.
OpenClaw CLI versions before 2026.3.7 contain a cross-account sender authorization scoping vulnerability in the `/allowlist ... --store` command. The issue arises because writes to the allowlist store did not properly scope the accountId, causing entries intended for one account to authorize senders on the default account. Exploitation requires an already-authorized user with permission to run `/allowlist` edits. The vulnerability is fixed in version 2026.3.7.
A sandbox boundary validation flaw in openclaw-cli versions up to 2026.2.25 allowed certain workspace-only write operations to bypass the sandbox boundary via dangling symlink alias handling. This could result in writes occurring outside the intended workspace or sandbox root, potentially compromising host file integrity. The issue is fixed in version 2026.2.26.
OpenClaw CLI in allowlist mode trusted PATH-derived directories for safe binary execution, allowing an attacker to bypass the allowlist by placing a same-name binary in a trusted directory. This could lead to command execution within the OpenClaw runtime context. The vulnerability affects openclaw versions up to 2026.2.21-2 and is planned to be fixed in version 2026.2.22. The root cause is trusting PATH-derived directories instead of explicit trusted directories and using shell command tokens that could resolve to shadowed binaries.
OpenClaw CLI versions from 2026.2.17 through 2026.2.24 contain a vulnerability in Telegram message_reaction handling that allows unauthorized users to inject reaction-derived system events. This occurs due to a missing sender-authorization check, bypassing configured direct message and group authorization policies. The issue is fixed in version 2026.2.25.
OpenClaw CLI versions up to 2026.2.22-2 have a stored cross-site scripting (XSS) vulnerability in the exported session HTML viewer. This occurs because raw HTML markdown tokens and unescaped metadata fields are rendered without proper sanitization, allowing attacker-controlled JavaScript to execute when opening a crafted exported session file. The vulnerability was patched in version 2026.2.23 by escaping raw HTML tokens and metadata fields and adding image MIME sanitization.
OpenClaw's macOS Dashboard flow exposed Gateway authentication credentials by including them in browser URL query parameters and storing them in localStorage. This allowed credentials to be accessible via browser address bar and persistent storage, increasing risk of unauthorized access. The vulnerability affects openclaw-cli versions up to 2026.3.2 and was fixed in version 2026.3.7 by changing token transport to URL fragments and removing persistent storage of tokens in the browser.