Sunday 26 July 2026 12:14:27 GMT+02:00
Netcrook
#source code exfiltration
Malicious AI Skills Are Becoming the New Trojan Horse in Agentic Workflows
A growing body of research shows that reusable AI agent skills can be weaponized to steal credentials, pull source code, and plant backdoors while slipping past weaker static checks.
One Token, One Door: The GitHub Intrusion That Turned Source Code Into Leverage
A compromised credential inside a GitHub environment can behave like a master key, and this incident shows how quickly access can become exfiltration and extortion.