From the source
When we launched ClawHub alongside OpenClaw, we were immediately targeted by actors who tried to publish skills bundling known malware.
We partnered with VirusTotal to flag those skills and ban the publishers automatically.
Traditional malware scanning is a relatively solved problem.
Identifying agentic risk is not.
A skill can claim to summarize your logs while bundling a script that ships them off your machine.
A well-meaning skill can point your agent at a CLI that wipes production on the wrong flag.
Neither of those is malware in the classic sense, and neither is something a virus scanner was built to catch.
So before installing a skill, you really want to know three things: What it claims to do.
Whether the bundled code actually matches that claim.
What the blast radius looks like if something goes wrong.
Answering those questions at the ecosystem scale is core to ClawHub’s mission.
To take full advantage of OpenClaw, our users need to trust that the skills and plugins they install have been thoroughly vetted.
…
