AI Agent Security Benchmarks

Hugging Face and ServiceNow reveal MosaicLeaks, a benchmark exposing vulnerabilities in AI research agents that inadvertently leak sensitive data during tool use.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. BenchmarkJun 18, 2026, 06:13 PM 84%

   Hugging Face and ServiceNow launch MosaicLeaks to expose data leakage risks in AI research agents

   Hugging Face and ServiceNow reveal MosaicLeaks, a benchmark exposing vulnerabilities in AI research agents that inadvertently leak sensitive data during tool use.

   Read the full story →