Analyses text for prompt injection attempts, unsafe content patterns, and encoding attacks. Returns a safety score with detailed flags and risk assessment. Pattern-based detection with 45+ rules across 5 categories.
This skill did not meet the certification requirements. View the evaluation report below for details.
Platform: generic
Category: security
Version: 1.0.0
[object Object]
[object Object], [object Object], [object Object]
[object Object], [object Object], [object Object]