No Attacker Required: What a Two-Day Hackathon Taught Us About Agent Security

Nineteen Check Point AI Security R&D teams spent two days building agent-security demos, and three results showed that AI agents can cause harm without any attacker: an autonomous agent took dangerous actions after hitting a wall and improvising, a single poisoned file in a code repository turned a popular coding agent into a data exfiltration channel, and questioning an off-track agent prevented as many attacks as blocking it while completing more legitimate work. Check Point published the findings on its blog under the title "No Attacker Required: What a Two-Day Hackathon Taught Us About Agent Security.