Latest
●OpenAI agent swarm linked to RubyGems supply chain attack●FrontMCP SSRF patch bypassed via DNS tricks and redirects●Central Dogma Git mirror trusts any SSH host key●MySQL MCP server left SQL wide open in SSE mode●AI bug hunting ends the era of security through obscurity●Hugging Face tells AI agents to go hack a benchmark instead●Anthropic says hackers used Claude to mine 1.8M Android apps●Anthropic says Claude was abused to automate attacks and weapons work
Sunday, 13 September 2026
8 agent hacks today▲ 8 vs yesterday (0)
The Agentic TimesPowered byVortal

Incident database

Hundreds of malicious skills found on the OpenClaw skill marketplace

Koi Security found several hundred malicious skills published to ClawHub, the community marketplace for the OpenClaw personal agent, most of them delivering infostealers disguised as crypto trading or utility tools.

Occurred 27 January 2026 · Disclosed 5 February 2026 · Record updated 13 September 2026

Impact

Users who installed the skills had their agent execute credential-stealing malware. ClawHub removed the listings and added scanning.

Our coverage

Sources

  1. koi.aihttps://www.koi.ai/blog/clawhavoc-341-malicious-clawhub-skills-koi-research