← all datasets

906-skill malicious-skill detection benchmark

Emerging
1papers using it
2026first seen

The '906-skill malicious-skill detection benchmark' is a dataset used to evaluate the presence of malicious intent in agent skills by analyzing deviations from declared capabilities.

Find this dataset

Papers using 906-skill malicious-skill detection benchmark (1)

906-skill malicious-skill detection benchmark dataset — papers, benchmarks & downloads · Cybersecurity