Least Privilege Design for Enterprise AI Agents
Stopping AI agent attacks means limiting what they can access in the first place.
Marcus Oduya
Staff Writer
Marcus Oduya
Marcus covers the intersection of enterprise software and AI supply-chain risk, drawing on a background in cloud infrastructure security and three years embedded with a threat intelligence firm. His reporting has been cited in multiple vendor security advisories.
3 stories
Prompt Injection Chains in Agentic Pipelines
Attackers chain prompt injections across agent systems to steal data and execute commands at scale.
Marcus Oduya
What an AI Risk Assessment Actually Needs to Test
Existing frameworks miss the hard part: finding and testing AI that's actually running.
Marcus Oduya