Companies and governments using AI agents need to anticipate and assess how their use can open them up to risks and affect operations, cybersecurity agencies in the USA, U.K. and Australia warned.
Agents that work autonomously can easily be misused and breached by hackers, leading to productivity losses and compromised private information, the Cybersecurity and Infrastructure Security Agency and organizations from other countries warned in a report released Friday.
- “Every individual component in an agentic AI system widens the attack surface, exposing the system to additional avenues of exploitation,” the report said.
- The agencies suggested a layered defense for AI ...