OpenClaw: risks for agent users and how to mitigate them
OpenClaw agent ecosystem faces 530+ CVEs and malicious skill attacks via ClawHub marketplace.
Kaspersky research reveals significant security risks in OpenClaw, a popular AI agent ecosystem used for task automation. The platform has accumulated approximately 530 vulnerabilities since its inception, with high-severity issues primarily involving sensitive data storage and privilege escalation. Beyond CVE exploits, attackers can distribute malicious skills through ClawHub, the official marketplace, creating a supply-chain-like attack vector that requires no malware development.
AI summary of the linked source. Not reviewed by an editor. How this works
Run Kaspersky?
Get an email when a new story names Kaspersky, usually within the hour.
Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy
The lesson from this incident
Full lessonThe OpenClaw platform has accumulated approximately 530 vulnerabilities, with high-severity issues centered on sensitive data exposure and privilege escalation — a dangerous combination in any AI-driven automation environment. More critically, attackers can publish malicious 'skills' through ClawHub, the platform's official marketplace, weaponizing the trusted distribution channel itself without writing traditional malware. This mirrors classic software supply chain attacks, where legitimacy is borrowed from a trusted source to bypass defenses. Organizations relying on AI agent ecosystems must recognize that the attack surface extends well beyond CVEs to include third-party content and plugins. Failing to vet marketplace components and delay patching in these environments can result in full compromise of automated workflows handling sensitive data.
What helps against this
How we list vendors- Vulnerability scanning and prioritisation
You know which systems are vulnerable, and which ones to fix first.
- AI application security
Prompt injection, data leaks through AI tools and unapproved AI use get caught.
- Software supply chain security
Malicious and vulnerable open-source packages are caught before they ship.