Fake AI Agent Skill Passed Security Scans and Reportedly Reached 26,000 Agents

A security firm created a fake AI agent skill and successfully uploaded it to a popular marketplace, where it was reportedly accessed by around 26,000 agents, including some linked to corporate accounts. The skill was promoted through an Instagram ad and passed security scans, with every scanner tested marking it as safe. The fake skill was designed to be harmless, collecting only the user's email address and performing no other actions. This experiment was intended to demonstrate a vulnerability, although the full implications are not specified. The firm's test highlights a potential security issue in the skill marketplace. The fact that the skill passed security scans despite being fake raises concerns.