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 2 of 18)

Severity CVE ID Summary CVSS Published
HIGH GHSA-p73f-w79w-jqr5 OpenClaw: owner-command auth bypass via native cmds -- Jul 2, 2026 HIGH GHSA-xww8-gqvh-92x9 OpenClaw: truncated approval UI masks exec payload 8.0 Jul 2, 2026 MEDIUM GHSA-qh2f-99mv-mrcf OpenClaw: exec denylist bypass in bundled MCP loopback -- Jul 2, 2026 HIGH GHSA-2j8v-hwgc-x698 OpenClaw: TOCTOU in shell wrapper bypasses command allowlist -- Jul 2, 2026 MEDIUM GHSA-9c3v-684m-579c OpenClaw: MCP SSE redirect leaks Authorization headers 6.5 Jul 1, 2026 HIGH CVE-2026-55249 @rtk-ai/rtk-rewrite: RCE via shell injection in exec tool 8.8 Jun 23, 2026 MEDIUM CVE-2026-40037 OpenClaw: request body replay leaks credentials via redirect 6.5 Apr 8, 2026 HIGH CVE-2026-35668 OpenClaw: sandbox path traversal exposes agent secrets 7.7 Apr 10, 2026 MEDIUM CVE-2026-35667 OpenClaw: SIGKILL bypass skips security-sensitive cleanup 6.1 Apr 10, 2026 MEDIUM CVE-2026-35664 OpenClaw: auth bypass enables unauthorized callback injection 5.3 Apr 10, 2026 HIGH CVE-2026-35666 OpenClaw: allowlist bypass enables arbitrary command exec 8.8 Apr 10, 2026 HIGH CVE-2026-35669 OpenClaw: privilege escalation via plugin scope bypass 8.8 Apr 10, 2026 HIGH CVE-2026-35663 OpenClaw: privilege escalation to admin via backend reconnect 8.8 Apr 10, 2026 MEDIUM CVE-2026-35665 OpenClaw: pre-auth resource exhaustion via Feishu webhook DoS 5.3 Apr 10, 2026 MEDIUM CVE-2026-35670 OpenClaw: webhook rebinding exposes user data 5.9 Apr 10, 2026 MEDIUM CVE-2026-35661 OpenClaw: auth bypass mutates AI agent session state 5.3 Apr 10, 2026 MEDIUM CVE-2026-35662 OpenClaw: missing auth enables agent scope bypass 4.3 Apr 10, 2026 MEDIUM CVE-2026-35656 OpenClaw: auth bypass via X-Forwarded-For spoofing 6.5 Apr 10, 2026 MEDIUM CVE-2026-35655 OpenClaw: identity spoofing bypasses agent safety checks 5.7 Apr 10, 2026 HIGH CVE-2026-35660 OpenClaw: auth bypass allows admin session hijacking 8.1 Apr 10, 2026 MEDIUM CVE-2026-35659 OpenClaw: DNS-SD metadata hijacks CLI routing 4.6 Apr 10, 2026 MEDIUM CVE-2026-35658 OpenClaw: sandbox bypass exposes host filesystem reads 6.5 Apr 10, 2026 HIGH CVE-2026-35650 OpenClaw: env var override bypass enables code execution 7.5 Apr 10, 2026 MEDIUM CVE-2026-35647 OpenClaw: access control bypass allows DM policy evasion 5.3 Apr 10, 2026 MEDIUM CVE-2026-35649 OpenClaw: access control bypass via allowlist reconciliation 6.5 Apr 10, 2026

Showing 26–50 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