Observed incident

Snyk confirmed malicious packages in the agent skills ecosystem

Reported

What happened

Snyk's audit of agent skills identified malicious payloads designed for credential theft, backdoor installation, and data exfiltration alongside a broader set of security weaknesses.

Parties and reporting

AI tools and systems: OpenClaw, ClawHub, Claude Code, Cursor, skills.sh

Outcome

Snyk reported 76 manually confirmed malicious payloads and eight still available on ClawHub at publication. It did not establish a complete victim count.

Operating lesson

Review skill contents and dependencies before installation, and limit the credentials and capabilities available to agents.

Evidence and limits

The larger 1,467 figure counts skills with security issues, not proven malware or victims. This study extends earlier malicious ClawHub campaign reporting.

Sources