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 3 of 18)

Severity CVE ID Summary CVSS Published
MEDIUM CVE-2026-35654 OpenClaw: auth bypass on Teams feedback invoke 5.3 Apr 10, 2026 MEDIUM CVE-2026-35652 OpenClaw: auth bypass enables unauthorized action execution 6.5 Apr 10, 2026 HIGH CVE-2026-35653 OpenClaw: auth bypass enables agent profile destruction 8.1 Apr 10, 2026 LOW CVE-2026-35648 OpenClaw: policy bypass via stale queued node actions 3.7 Apr 10, 2026 HIGH CVE-2026-35641 OpenClaw: RCE via .npmrc override in plugin install 7.8 Apr 10, 2026 HIGH CVE-2026-35643 OpenClaw: WebView bridge injection enables Android RCE 8.8 Apr 10, 2026 MEDIUM CVE-2026-35642 OpenClaw: auth bypass injects restricted agent events 4.3 Apr 9, 2026 HIGH CVE-2026-35645 OpenClaw: privilege escalation via synthetic admin session scope 8.1 Apr 9, 2026 HIGH CVE-2026-35639 OpenClaw: scope bypass enables admin RCE via device pairing 8.8 Apr 9, 2026 MEDIUM CVE-2026-35644 OpenClaw: credential exposure via gateway channel URLs 6.5 Apr 9, 2026 MEDIUM CVE-2026-35636 OpenClaw: session isolation bypass exposes parent sessions 6.5 Apr 9, 2026 MEDIUM CVE-2026-35633 OpenClaw: unbounded memory alloc DoS via crafted HTTP errors 5.3 Apr 9, 2026 MEDIUM CVE-2026-35635 OpenClaw: webhook route hijack bypasses DM access controls 4.8 Apr 9, 2026 MEDIUM CVE-2026-35631 OpenClaw: auth bypass on ACP mutating commands 6.5 Apr 9, 2026 HIGH CVE-2026-35632 OpenClaw: symlink traversal enables RCE via agent config 7.1 Apr 9, 2026 HIGH CVE-2026-35637 OpenClaw: auth bypass via premature cite expansion 7.3 Apr 9, 2026 MEDIUM CVE-2026-35634 OpenClaw: auth bypass grants unauthenticated Canvas access 5.1 Apr 9, 2026 HIGH CVE-2026-35638 OpenClaw: priv escalation via trusted-proxy scope bypass 8.8 Apr 9, 2026 MEDIUM CVE-2026-35622 OpenClaw: auth bypass in Google Chat webhook 5.9 Apr 9, 2026 MEDIUM CVE-2026-35628 OpenClaw: webhook brute-force bypasses AI agent auth 4.8 Apr 9, 2026 HIGH CVE-2026-35625 OpenClaw: privilege escalation to RCE via silent reconnect 7.8 Apr 9, 2026 MEDIUM CVE-2026-35626 OpenClaw: unauthenticated DoS via webhook body buffering 5.3 Apr 9, 2026 MEDIUM CVE-2026-35627 OpenClaw: pre-auth DoS via Nostr DM resource exhaustion 6.5 Apr 9, 2026 MEDIUM CVE-2026-35624 OpenClaw: auth bypass exposes protected Talk rooms 4.2 Apr 9, 2026 MEDIUM CVE-2026-35623 OpenClaw: Brute-force auth bypass via webhook rate limit miss 4.8 Apr 9, 2026

Showing 51–75 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