OpenClaw
CVE-2026-62195
HIGH
Severity by source
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Network-reachable, low-complexity authorization bypass by an already-authenticated low-trust caller (PR:L), yielding high confidentiality/integrity and minor availability impact with no scope change.
Primary rating from Vendor (VulnCheck).
CVSS VectorVendor: VulnCheck
Lifecycle Timeline
2DescriptionCVE.org
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 execute or persist actions beyond their intended permissions.
AnalysisAI
Authorization bypass in OpenClaw 2026.5.20 through 2026.6.5 lets a low-privilege caller invoke owner-only tools through the MCP loopback feature, escalating beyond intended permissions to execute or persist privileged actions. The flaw stems from incorrect permission enforcement (CWE-732) on configured input paths reachable over the network. No public exploit identified at time of analysis, and it is not listed in CISA KEV.
Technical ContextAI
OpenClaw exposes a Model Context Protocol (MCP) loopback interface intended to let trusted local components invoke tools. The vulnerability is a CWE-732 (Incorrect Permission Assignment for a Critical Resource) issue: the loopback path fails to re-validate the trust level of the caller before dispatching tools that are gated to the owner/operator role. Because certain configured input paths route requests into the loopback handler, a lower-trust actor's request is treated as if it originated from a trusted context, so owner-only tool authorization checks are effectively skipped. The single affected component is the OpenClaw application itself (cpe:2.3:a:openclaw:openclaw:*), with no dependent library implicated by the available data.
RemediationAI
Vendor-released patch: 2026.6.6 - upgrade OpenClaw to 2026.6.6 or later, which contains the fixed authorization enforcement per GHSA-52xj-c9p8-78cv (https://github.com/openclaw/openclaw/security/advisories/GHSA-52xj-c9p8-78cv). If immediate upgrade is not possible, reduce exposure by restricting network reachability of the MCP loopback interface to trusted local processes only (for example bind it to localhost/a Unix socket and firewall any TCP exposure), and audit or disable the configured input paths that route external requests into the loopback handler; the trade-off is that legitimate integrations relying on those input paths will break until reconfigured. Tighten account provisioning so low-trust callers cannot obtain the PR:L foothold the attack requires, and review logs for unexpected invocation of owner-only tools. Corroborating detail is available in the VulnCheck advisory at https://www.vulncheck.com/advisories/openclaw-authorization-bypass-via-mcp-loopback.
Auth bypass in OpenClaw voice-call extension before 2026.2.1. EPSS 0.68%. PoC and patch available.
Privilege escalation in OpenClaw (pre-2026.3.28) allows unauthenticated remote attackers to gain administrative access b
OpenClaw versions 2026.2.22 through 2026.2.24 contain a privilege escalation vulnerability that allows authenticated att
An authorization mismatch vulnerability in OpenClaw versions prior to 2026.3.1 allows authenticated users with operator.
OpenClaw versions prior to 2026.1.29 automatically establish WebSocket connections to attacker-controlled gateway URLs e
Path traversal in OpenClaw through version 2026.3.23 enables unauthenticated remote attackers to read arbitrary files in
OpenClaw sandbox browser functionality launches x11vnc for noVNC observer sessions without requiring authentication, all
OpenClaw versions before 2026.2.26 allow authenticated attackers to write arbitrary files outside the workspace director
OpenClaw versions prior to 2026.2.22 contain a shell environment variable injection vulnerability in the system.run func
OpenClaw versions prior to 2026.2.22 contain a resource exhaustion vulnerability where the application fails to consiste
OpenClaw versions prior to 2026.3.1 contain a sandbox escape vulnerability that allows authenticated attackers with low
OpenClaw versions 2026.1.30 and below fail to validate Telegram webhook secret tokens when `channels.telegram.webhookSec
Same technique Authentication Bypass
View allShare
External POC / Exploit Code
Leaving vuln.today