How Dangerous Are AI Agents Mimicking You? AntiSkillBench Reveals Privacy Risks

Yongli Xiang · hf · 2026-08-05

As AI agents learn to distill personal interaction histories into reusable "persona skills", the associated privacy and security risks intensify. A new paper introduces AntiSkillBench, an end-to-end benchmark designed to evaluate risks and defenses within the persona-skill pipeline.

The benchmark features:

Experiments across three frontier agents show that privacy risks persist universally, while existing defenses offer limited, distillation-dependent effectiveness.

Original post →

More from Safety

Safety channel →