Malicious Agent Skills: Authorized Actions, Hidden Intent & the Skills Factory | Ep 19

The Threat Intelligence Podcast · Oct 9, 2026 · 26m

AI agents are only as trustworthy as the skills they load. Yi Liu, AI research engineer at Common Defense and PhD researcher at Nanyang Technological University, joins Rachel James and Dr. Bryan Nakayama to explain what he found after analyzing nearly 100,000 agent skills.

The result: 157 confirmed malicious skills, including one that quietly added an attacker to outgoing email and told the agent never to mention it. We cover prompt injection inside skills, benign pieces that combine into harmful behavior, memory-based attacks that trigger in later sessions, and the single “skills factory”…