Skip to content
OpenAdvisories
High WID-SEC-2026-2133 44 CVEs

OpenClaw: Mehrere Schwachstellen

Published Jun 29, 2026 · Updated Jul 16, 2026 · Revision 4 · de-DE

Summary

Ein Angreifer kann mehrere Schwachstellen in OpenClaw ausnutzen, um erweiterte Rechte zu erlangen, beliebigen Code auszuführen, Sicherheitsmaßnahmen zu umgehen, Daten offenzulegen oder zu manipulieren oder andere, nicht näher spezifizierte Angriffe durchzuführen.

Product

OpenClaw ist ein persönlicher KI-Assistent zur Ausführung auf eigenen Geräten.

Vulnerabilities 44

  • High 8.8

    OpenClaw < 2026.6.9 Authorization Bypass via flock wrapper

    OpenClaw versions before 2026.6.9 contain an authorization bypass vulnerability in the flock wrapper that allows lower-trust callers to execute or persist actions beyond their intended authorization. Attackers can leverage configured input paths to bypass dur…

  • High 8.8

    OpenClaw 2026.5.20 < 2026.6.9 Privilege Escalation via Plugin Install

    OpenClaw versions 2026.5.20 before 2026.6.9 contain a privilege escalation vulnerability in plugin install commands that allows lower-trust callers to execute or persist actions beyond their intended authorization. Attackers can exploit misconfigured input pa…

  • High 8.8

    OpenClaw < 2026.6.6 Authentication Bypass via Environment Filtering

    OpenClaw versions before 2026.6.6 contain a flaw in host exec environment filtering that can miss interpreter startup variables. When the affected feature is enabled and reachable, a lower-trust caller or configured input path can supply crafted environment v…

  • High 8.8

    OpenClaw < 2026.6.6 Authentication Bypass via Git ext transport

    OpenClaw versions before 2026.6.6 contain a flaw in host exec environment filtering that could allow Git ext transport to be abused. When the affected feature is enabled and reachable, a lower-trust caller or configured input path could execute or persist act…

  • High 8.8

    OpenClaw 2026.6.1 < 2026.6.9 Privilege Escalation via Cron

    OpenClaw versions 2026.6.1 before 2026.6.9 contain a privilege escalation vulnerability in isolated cron jobs that allows lower-trust callers to regain denied execution tools. Attackers can execute or persist actions beyond their intended authorization by lev…

  • High 8.8

    OpenClaw < 2026.6.6 Environment Variable Injection via rustup

    OpenClaw versions before 2026.6.6 contain an environment variable filtering vulnerability in host exec that fails to properly sanitize rustup startup variables. Attackers with lower-trust caller access or configured input paths can execute or persist actions …

  • High 8.8

    OpenClaw < 2026.6.5 Authentication Bypass via Admin Tools

    OpenClaw versions before 2026.6.5 contain an authentication bypass vulnerability that allows lower-trust callers to reach admin-scoped tools. Attackers can perform actions requiring stronger authorization by exploiting insufficient policy checks on configured…

  • High 8.8

    OpenClaw 2026.5.14-beta.1 < 2026.5.27 Authentication Bypass via exec approvals

    OpenClaw 2026.5.14-beta.1 before 2026.5.27 contain an authorization flaw in the QQBot exec approvals feature. When the feature is enabled and reachable, a lower-trust caller or configured input path could execute or persist actions beyond the caller's intende…

  • High 8.8

    OpenClaw 2026.1.20 < 2026.5.27 Authorization Bypass via device.pair.approve

    OpenClaw 2026.1.20 before 2026.5.27 contain an authorization bypass vulnerability in the device.pair.approve feature that allows lower-trust callers to bypass role-management checks. Attackers can perform actions requiring stronger authorization by reaching t…

  • High 8.8

    OpenClaw < 2026.5.18 Authorization Bypass via Device-pair

    OpenClaw before 2026.5.18 contain an authorization bypass vulnerability in the device-pair approval feature that allows lower-trust callers to execute actions beyond their intended authorization. Attackers can exploit misconfigured input paths to execute or p…

  • High 8.8

    OpenClaw < 2026.6.5 Authorization Bypass via Node Exec Approvals

    OpenClaw before 2026.6.5 contain an authorization bypass vulnerability in node exec approvals that allows lower-trust callers to execute actions beyond their intended authorization by using different gateway and node environments. Attackers can exploit mismat…

  • High 8.8

    OpenClaw < 2026.5.18 Authorization Bypass via Glob Matching

    OpenClaw before 2026.5.18 contain an authorization bypass vulnerability in exec allowlist glob matching that allows lower-trust callers to execute actions beyond intended authorization. Attackers can craft input paths that traverse the allowlist glob patterns…

  • High 8.5

    OpenClaw < 2026.6.6 Policy Bypass via CDP Discovery

    OpenClaw before 2026.6.6 contains a policy bypass vulnerability in browser CDP discovery that accepts blocked WebSocket URLs. Attackers with lower-trust access can reach network destinations that should have been blocked by OpenClaw policy when the affected f…

  • High 8.5

    OpenClaw 2026.3.28 < 2026.5.19 Authorization Bypass via Browser Act Route

    OpenClaw 2026.3.28 before 2026.5.19 contain an authorization bypass vulnerability in the browser act route that fails to properly validate current-tab URL checks. Attackers with lower-trust access or configured input paths can perform actions requiring strong…

  • High 8.3

    OpenClaw 2026.5.20 < 2026.6.6 Authorization Bypass via MCP loopback

    OpenClaw versions 2026.5.20 before 2026.6.6 contain an authorization bypass vulnerability in the MCP loopback feature that allows lower-trust callers to execute owner-only tools. Attackers can bypass authorization checks through configured input paths to exec…

  • High 8.3

    OpenClaw 2026.3.22 < 2026.6.6 Authorization Bypass via WhatsApp Group IDs

    OpenClaw versions 2026.3.22 before 2026.6.6 contain an authorization bypass vulnerability where WhatsApp group IDs can satisfy elevated sender allowlists. Attackers with lower-trust access can perform actions requiring stronger authorization by leveraging gro…

  • High 8.1

    OpenClaw < 2026.6.9 Feishu tools Authorization Bypass

    OpenClaw Feishu tools (npm package @openclaw/feishu) in versions <= 2026.6.6 could ignore per-account disablement. A lower-trust caller or a configured input path could perform actions that should have required a stronger authorization or policy check, result…

  • High 8.1

    OpenClaw < 2026.6.9 Feishu Authorization Bypass

    OpenClaw @openclaw/feishu versions 2026.6.6 and earlier contain an incorrect authorization vulnerability in which the Feishu permission tools could ignore per-account disablement settings. When the affected feature is enabled and reachable, a lower-trust call…

  • High 8.1

    OpenClaw 2026.6.6 < 2026.6.9 Authorization Bypass

    OpenClaw versions 2026.6.6 before 2026.6.9 contain an authorization bypass vulnerability in Discord guild actions that allows lower-trust callers to perform actions requiring stronger authorization checks. Attackers can exploit misconfigured input paths to sk…

  • High 8.1

    OpenClaw 2026.5.10-beta.1 < 2026.6.5 Authorization Bypass via agent-mode dispatch

    OpenClaw versions 2026.5.10-beta.1 before 2026.6.5 contain an authorization bypass in the ClickClack agent-mode dispatch feature, which could ignore the toolsAllow policy check. When the affected feature is enabled and reachable, a lower-trust caller or confi…

  • High 8.0

    OpenClaw < 2026.6.5 Authentication Bypass via HTTP Canvas

    OpenClaw versions before 2026.6.5 contain an authentication bypass vulnerability in HTTP Canvas responses that allows lower-trust callers to forge trusted A2UI actions. Attackers can perform actions requiring stronger authorization by submitting crafted reque…

  • High 7.8

    OpenClaw < 2026.5.22 Untrusted Plugin Loading via Setup-mode

    OpenClaw before 2026.5.22 contain a vulnerability in setup-mode discovery that allows loading of untrusted workspace plugins. Attackers with lower-trust caller access or control over configured input paths can execute or persist actions beyond their intended …

  • High 7.7
    CVE-2026-62201 Public exploit

    OpenClaw < 2026.6.6 Network Policy Bypass via exec-server

    OpenClaw versions before 2026.6.6 contain a network policy bypass vulnerability in the sandbox exec-server that allows lower-trust callers to reach internal network destinations blocked by OpenClaw policy. Attackers can send HTTP requests through the exec-ser…

  • High 7.7

    OpenClaw 2026.4.14 < 2026.5.26 SSRF via Browser Snapshot

    OpenClaw 2026.4.14 before 2026.5.26 contain a server-side request forgery vulnerability in browser snapshot routes that fail to validate post-navigation destinations. Attackers with lower-trust access can bypass OpenClaw policy checks to reach network destina…

  • High 7.6

    OpenClaw < 2026.6.8 Authorization Bypass via HTTP Model Override

    OpenClaw versions before 2026.6.8 contain an authorization bypass vulnerability in OpenAI-compatible HTTP model overrides that allows lower-trust callers to perform actions requiring stronger authorization checks. Attackers can exploit misconfigured input pat…

  • High 7.1

    OpenClaw < 2026.5.28 - Credential Override via Workspace Dotenv Files

    OpenClaw before 2026.5.28 contains a credential exposure vulnerability where workspace dotenv files can override provider credentials. Attackers with lower-trust access to configured input paths can expose sensitive data and credentials that should remain wit…

  • High 7.1

    OpenClaw < 2026.6.9 Symlink Following via Mirror Sync

    OpenClaw versions before 2026.6.9 contain a symlink following vulnerability in the mirror sync feature that allows lower-trust callers to perform actions requiring stronger authorization. Attackers can exploit remote symlink parents to bypass policy checks an…

  • High 7.1

    OpenClaw 2026.6.6 < 2026.6.9 Authorization Bypass via Message Mutations

    OpenClaw versions 2026.6.6 before 2026.6.9 contain an authorization bypass vulnerability in message mutation handling that allows lower-trust callers to perform actions requiring stronger authorization checks. Attackers can exploit misconfigured input paths t…

  • High 7.1

    OpenClaw 2026.4.12-beta.1 < 2026.6.6 Authorization Bypass via message actions

    OpenClaw versions 2026.4.12-beta.1 before 2026.6.6 contain a missing-authorization vulnerability in the MS Teams message actions feature. When the affected feature is enabled and reachable, a lower-trust caller or a configured input path can perform actions t…

  • High 7.1

    OpenClaw < 2026.6.9 Authentication Bypass via Moderation Actions

    OpenClaw versions before 2026.6.9 contain a missing authorization vulnerability in Discord moderation actions. In affected versions, a lower-trust caller or configured input path could perform moderation actions that should have required a stronger authorizat…

  • High 7.1

    OpenClaw < 2026.5.28 Authentication Bypass via safeFetch

    OpenClaw before 2026.5.28 contains a race condition in the MS Teams safeFetch DNS rebinding check. When the affected feature is enabled and reachable, a lower-trust caller or configured input path could win a timing window between the DNS validation check and…

  • High 7.1

    OpenClaw 2026.2.12 < 2026.5.26 Authorization Bypass via Blank Agent IDs

    OpenClaw 2026.2.12 before 2026.5.26 contain an authorization bypass vulnerability in the hooks allowedAgentIds validation. A lower-trust caller or configured input path can bypass agent ID restrictions by submitting blank agent IDs, allowing actions that shou…

  • Medium 6.5

    OpenClaw < 2026.6.5 Authorization Header Forwarding via SSE

    OpenClaw before 2026.6.5 could forward Authorization headers during MCP SSE redirects. When the affected feature is enabled and reachable, a lower-trust caller or configured input path could execute or persist actions beyond the caller's intended authorizatio…

  • Medium 6.5

    OpenClaw < 2026.6.1 Denial of Service via Remote Media URLs

    OpenClaw versions before 2026.6.1 contain a denial of service vulnerability where remote media URLs can trigger slow-read attacks that exhaust gateway worker resources. Attackers with access to configured input paths can supply remote media URLs that consume …

  • Medium 6.5

    OpenClaw < 2026.5.27 Token Leakage via MS Teams Outbound Requests

    OpenClaw versions before 2026.5.27 contain a token leakage vulnerability in MS Teams outbound requests that allows lower-trust callers to expose Bot Framework tokens. Attackers can access configured input paths to retrieve credentials that should remain withi…

  • Medium 6.5

    OpenClaw < 2026.5.28 Bot Framework SSRF via serviceUrl Parameter Validation

    OpenClaw versions before 2026.5.28 Bot Framework contains an improper input validation vulnerability that allows lower-trust callers to expose bot tokens and credentials by failing to properly validate serviceUrl parameters. Attackers can supply malicious ser…

  • Medium 5.4

    OpenClaw 2026.5.12 < 2026.5.26 Authorization Bypass via allowFrom

    OpenClaw 2026.5.12 before 2026.5.26 contain an incorrect authorization vulnerability in the ClickClack allowFrom feature. When the affected feature is enabled and reachable, a lower-trust caller or configured input path could execute or persist actions beyond…

  • Medium 5.4

    OpenClaw MS Teams < 2026.5.12 Authorization Bypass

    OpenClaw MS Teams before 2026.5.12 contain an authorization bypass vulnerability where the allowFrom feature binds to mutable display names. Attackers with lower-trust access can perform actions requiring stronger authorization by exploiting the mutable displ…

  • Medium 5.4

    OpenClaw < 2026.5.18 Authorization Bypass via Skill Command Dispatch

    OpenClaw versions before 2026.5.18 contain an authorization bypass vulnerability in skill command dispatch that allows lower-trust callers to execute or persist actions beyond their intended authorization. Attackers can bypass tool policy restrictions through…

  • Medium 5.3

    OpenClaw 2026.2.25 < 2026.5.26 WebSocket Rate Limit Bypass

    OpenClaw 2026.2.25 before 2026.5.26 allow a lower-trust caller or configured input path to bypass non-browser rate limits on WebSocket authentication attempts. When the affected feature is enabled and reachable by lower-trust input, this can consume gateway r…

  • Medium 5.0

    OpenClaw < 2026.6.1 Credential Redaction Bypass via Trajectory Export

    OpenClaw versions before 2026.6.1 contain a credential redaction bypass vulnerability in the trajectory export feature that allows lower-trust callers to access data that should remain within trusted boundaries. Attackers can exploit misconfigured input paths…

  • Medium 5.0

    OpenClaw 2026.4.20 < 2026.5.28 Policy Bypass via Media Upload

    OpenClaw 2026.4.20 before 2026.5.28 contain a policy bypass in the QQBot media upload feature. A lower-trust caller or configured input path could cause the media upload to reach network destinations that should have been blocked by OpenClaw policy (server-si…

  • Medium 4.9

    OpenClaw 2026.6.5 < 2026.6.9 Authentication Bypass via Plugin Install

    OpenClaw versions 2026.6.5 before 2026.6.9 contain a vulnerability in the plugin install wrappers that could skip the install policy (authorization) check. When the affected feature is enabled and reachable, a lower-trust caller or a configured input path cou…

  • Medium 4.3

    OpenClaw 2026.5.28 < 2026.6.6 Authorization Bypass via Web Search

    OpenClaw versions 2026.5.28 before 2026.6.6 contain an authorization bypass vulnerability in native web search that allows lower-trust callers to perform actions requiring stronger policy checks. Attackers can exploit misconfigured input paths to bypass inten…

Revision history

  1. #4

    Referenz(en) aufgenommen: GHSA-Q7VF-83CX-XC54, CVE-2026-62229, EUVD-2026-45117, CVE-2026-62228, EUVD-2026-45116, CVE-2026-62227, EUVD-2026-45115, CVE-2026-62226, EUVD-2026-45114, CVE-2026-62225, EUVD-2026-45113, CVE-2026-62224, EUVD-2026-45112, CVE-2026-62221, EUVD-2026-45109, CVE-2026-62220, EUVD-2026-45108, CVE-2026-62219, EUVD-2026-45107, CVE-2026-62218, EUVD-2026-45106, CVE-2026-62217, EUVD-2026-45105, CVE-2026-62216, EUVD-2026-45104, CVE-2026-62215, EUVD-2026-45103, CVE-2026-62214, EUVD-2026-45102, CVE-2026-62213, EUVD-2026-45101, CVE-2026-62212, EUVD-2026-45100, GHSA-VQ5X-R5HJ-W7QC, GHSA-8X5V-5GH2-QR2J, CVE-2026-62211, EUVD-2026-45099, CVE-2026-62210, EUVD-2026-45098, CVE-2026-62209, EUVD-2026-45097, CVE-2026-62208, EUVD-2026-45096, CVE-2026-62207, EUVD-2026-45095, CVE-2026-62206, EUVD-2026-45094, CVE-2026-62205, EUVD-2026-45093, CVE-2026-62203, EUVD-2026-45092, CVE-2026-62202, EUVD-2026-45091, CVE-2026-62201, EUVD-2026-45090, CVE-2026-62222, EUVD-2026-45110, GHSA-WW99-RC68-X2PJ

  2. #3

    Referenz(en) aufgenommen: CVE-2026-62195, EUVD-2026-43535, CVE-2026-62187, EUVD-2026-43565, CVE-2026-62194, EUVD-2026-43534, CVE-2026-62192, EUVD-2026-43570, CVE-2026-62200, EUVD-2026-43540, CVE-2026-62191, EUVD-2026-43569, CVE-2026-62189, EUVD-2026-43567, CVE-2026-62196, EUVD-2026-43536, CVE-2026-62197, EUVD-2026-43537, CVE-2026-62199, EUVD-2026-43539, CVE-2026-62198, EUVD-2026-43538, CVE-2026-62188, EUVD-2026-43566, CVE-2026-62193, EUVD-2026-43571, CVE-2026-62190, EUVD-2026-43568, CVE-2026-62186, EUVD-2026-43564

  3. #2

    Referenz(en) aufgenommen: CVE-2026-59261, EUVD-2026-42322

  4. #1

    Initiale Fassung

References