AI Threat Alert

OpenClaw Vulnerabilities

pip AI Agents

AI Threat Alert tracks 427 known vulnerabilities in OpenClaw, 15 rated critical — an AI/ML ai agents in the pip ecosystem. Each CVE includes CVSS severity, EPSS exploit probability, patch status, and CISO-grade analysis.

Data sources
427
Total CVEs
15
Critical
pip
Ecosystem
Jul 8, 2026
Last CVE
41%
Patch Rate
3d
Avg Time to Patch

Known Vulnerabilities (427 total, page 11 of 18)

Severity CVE ID Summary CVSS Published
HIGH CVE-2026-53840 OpenClaw: credential exfiltration via MCP header forwarding 7.1 Jun 16, 2026 CRITICAL CVE-2026-53838 OpenClaw: approval scope bypass via reconnection state 9.8 Jun 12, 2026 HIGH CVE-2026-53836 OpenClaw: PowerShell allowlist bypass enables arbitrary RCE 8.8 Jun 12, 2026 LOW CVE-2026-53837 OpenClaw: DM policy bypass via Mattermost event spoofing 3.7 Jun 12, 2026 MEDIUM CVE-2026-53835 OpenClaw: auth bypass in Feishu agent binding controls 4.3 Jun 12, 2026 HIGH CVE-2026-53834 OpenClaw: auth bypass in QQBot pre-dispatch commands 7.5 Jun 12, 2026 MEDIUM CVE-2026-53839 OpenClaw: hostname prefix bypass leaks auth tokens 6.5 Jun 12, 2026 HIGH CVE-2026-53829 OpenClaw: approval truncation bypasses exec oversight 8.0 Jun 12, 2026 MEDIUM CVE-2026-53830 OpenClaw: stale webhook secrets bypass revocation 6.5 Jun 12, 2026 HIGH CVE-2026-53833 OpenClaw: auth bypass allows agent config mutation 7.7 Jun 12, 2026 HIGH CVE-2026-53832 OpenClaw: identity header spoof grants operator access 7.7 Jun 12, 2026 MEDIUM CVE-2026-53827 OpenClaw: SSRF leaks Gateway credentials via model metadata 6.5 Jun 12, 2026 HIGH CVE-2026-53828 OpenClaw: auth bypass enables owner command execution 8.8 Jun 12, 2026 MEDIUM CVE-2026-53826 OpenClaw: workspace path leaked from sandboxed sessions 4.3 Jun 12, 2026 HIGH CVE-2026-53831 OpenClaw: safe-bin allowlist bypass via shell expansion 8.3 Jun 12, 2026 MEDIUM CVE-2026-53825 OpenClaw: path traversal exposes local files via wiki ingest 6.5 Jun 12, 2026 HIGH CVE-2026-53823 OpenClaw: privilege escalation via Slack display name spoofing 8.1 Jun 12, 2026 HIGH CVE-2026-53821 OpenClaw: auth bypass grants admin RPC via WebSocket 8.8 Jun 12, 2026 MEDIUM CVE-2026-53824 OpenClaw: stale slash tokens bypass revocation controls 6.5 Jun 12, 2026 HIGH CVE-2026-53822 OpenClaw: TOCTOU command injection bypasses allowlist 8.8 Jun 12, 2026 MEDIUM CVE-2026-53820 OpenClaw: exec denylist bypass via MCP session-spawn 6.6 Jun 12, 2026 MEDIUM CVE-2026-53818 OpenClaw: MCP loopback auth bypass enables policy evasion 6.6 Jun 11, 2026 HIGH CVE-2026-53814 OpenClaw: privilege escalation via hook-triggered MCP scope 8.3 Jun 11, 2026 HIGH CVE-2026-53817 OpenClaw: locality spoof yields durable admin credentials 8.8 Jun 11, 2026 MEDIUM CVE-2026-53815 OpenClaw: auth bypass exposes restricted channel messages 6.5 Jun 11, 2026

Showing 251–275 of 427

← Previous Next →

Frequently asked questions

What is OpenClaw?

OpenClaw is an AI/ML ai agents tracked by AI Threat Alert for security vulnerabilities in the pip ecosystem.

How many known vulnerabilities does OpenClaw have?

OpenClaw has 427 known CVEs, 15 of them critical, tracked from NVD and GitHub Advisory.

Which ecosystem is OpenClaw distributed in?

OpenClaw is distributed via the pip ecosystem and categorized as ai agents.

Where does the OpenClaw vulnerability data come from?

Vulnerability data is sourced from NVD and GitHub Advisory, enriched with CVSS, EPSS, exploit signals, and patch status for each CVE.

How do I assess the risk of OpenClaw?

Review each CVE below — every entry shows CVSS severity, EPSS exploit probability, exploitation signals, and whether a patched version is available.

Monitor OpenClaw in your stack

Get instant alerts when new vulnerabilities affect OpenClaw. CISO analysis, ATLAS technique mappings, and compliance reports included.

Start Monitoring