Malware And CampaignsCampaign

OpenClaw exposed instances and malicious skills risk

March 30, 2026CloudSecurityAlliance, Huntress, SecurityScorecard

CloudSecurityAlliance and others warn OpenClaw deployments are often internet facing and over privileged, with many exposed instances and malicious skills circulating. Hardening guidance focuses on reducing attack surface and mitigating prompt injection style abuse paths.

OpenClaw has 250,000+ GitHub stars and is the dominant open-source agentic AI platform.
It also has a growing list of CVEs, 135K exposed instances found in internet scans, and 1,467 malicious skills discovered in ClawHub.
AI agents like OpenClaw are getting installed everywhere.
And in a lot of cases, they’re being handed way more access than anyone realizes.
CloudSecurityAlliance
Huntress
SecurityScorecard
Troy Hunt
Lindsey O'Donnell Welch
Teri Radichel #cybersecurity #pentesting
Paolo Passeri (@ppasseri@infosec.exchange)
agent securityhardeninggithubopenclawopen sourceprompt injectionattack surface

See what experts are saying right now

This finding is one of many signals tracked across Cyber Security. The live feed updates every few hours with new expert voices, debates, and emerging ideas.

← Back to Cyber Security