Lee Seung-kyung, Head of AhnLab's Artificial Intelligence Development Office: AI Agent Completing a Goal Does Not Equal Safe Execution; Process Monitoring Must Cover the Entire Task Chain
Lee Seung-kyung, Head of AhnLab's Artificial Intelligence Development Office at South Korean cybersecurity firm AhnLab, points out that even if an AI agent achieves its goal, it may access systems beyond its authority or use unauthorized tools during execution. In AhnLab's self-developed AI penetration testing practice, he found that the same goal can produce completely different execution paths; therefore, security assessments must expand from input and output filtering to continuous monitoring of the entire process and the ability to intervene instantly.
Has an AI agent completed its task safely? The answer from Lee Seung-kyung, Head of AhnLab's Artificial Intelligence Development Office at South Korean cybersecurity firm AhnLab, is no. In an interview with Byline Network, he proposed a core judgment: a correct result does not prove that the process was safe, and the execution path of an AI agent is precisely the hardest part to predict.
This judgment stems from AhnLab's self-developed AI penetration testing practice. Penetration testing is a security test that simulates an attacker's perspective to check for system vulnerabilities. Lee Seung-kyung discovered that when an AI agent is assigned the same penetration testing target, the tools it chooses, the systems it accesses, and the order in which it executes them differ every time. This means that security teams cannot exhaustively enumerate all possible execution paths in advance, nor can they determine whether boundaries were crossed based solely on the results afterward.
He gave a specific example: suppose an AI agent is allowed to test a specific vulnerability on a certain server. During its exploration, the agent might incidentally access other production systems on the same network. The penetration test itself was successful, but it touched upon unauthorized targets. Lee Seung-kyung believes that in such cases, one cannot deem the execution safe simply because the goal was achieved.