"ClawSwarm isn't a vulnerability disclosure. There's no flaw to patch and nothing covert about the infrastructure. It's an open source project on GitHub with public docs, a Telegram group, and a token on a public chain."
"The campaign sees a user install a seemingly benign skill - these purport to be everything from a cron helper to an Agent Security skill, a whale watcher, a cross-platform poster, and a predictions market integration."
"After registering itself with the external server, the agent follows the instructions in a SKILL.md file and therefore reports its name and capabilities to the third-party, along with what skills it has installed."
Thirty ClawHub skills published by a user are creating a cryptocurrency mining swarm by co-opting AI agents. This campaign, named ClawSwarm, targets agents and SKILL.md files rather than humans. Users unknowingly install benign-seeming skills, which lead agents to register with an external server and report their capabilities. The agents generate crypto wallets and store credentials without user approval, making the entire process covert and undetectable to the human user.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]