DEV Community

Daniel Samer
Daniel Samer

Posted on • Originally published at clawhosters.com

CrowdStrike Calls OpenClaw 'AI Super Agent', Publishes 156 Security Advisories

CrowdStrike's CTO Elia Zaitsev just published what might be the most thorough security breakdown of OpenClaw to date. They're not treating it as a chatbot. They're treating it as an autonomous system with real access to real infrastructure.

The Numbers

156 total security advisories. 28 with CVE IDs assigned, 128 still awaiting assignment.

Severity breakdown: 4 Critical, 52 High, 88 Medium, 12 Low. That's 56 advisories rated High or Critical.

Four Attack Vectors

CrowdStrike identified:

  1. Direct prompt injection where attackers feed malicious instructions to the agent
  2. Indirect prompt injection through contaminated data sources
  3. Agentic tool chain attacks exploiting how OpenClaw connects to external systems
  4. AI tool poisoning targeting plugins and skills

As Zaitsev put it: "AI agents don't just generate answers, they can take action; operating with speed, autonomy, and privileged access to email, calendars, sensitive data, credentials, and third-party systems."

The Scale Problem

Censys found 21,639 publicly accessible OpenClaw instances. Most probably running without dedicated security monitoring or regular patching.

CrowdStrike also demoed their Falcon AIDR blocking a live Discord exfiltration attack targeting an OpenClaw instance. These aren't theoretical risks.

What This Means

If you're running OpenClaw on a VPS you set up months ago, 56 High/Critical advisories should make you uncomfortable. Self-hosted AI without professional security management is becoming a liability.

Full breakdown

Managed hosting like ClawHosters applies auto-patching, credential isolation, and monitoring as standard. The kinds of protections CrowdStrike recommends, applied automatically.

Top comments (0)