Prompt Check
Classify a single prompt across 14 safety categories.
Total checks
—
all-time
Unsafe blocked
—
—
Avg latency
—
last 50 checks
Bypass attempts
—
obfuscation caught
Sessions
Shield-guarded chat — —
Dataset stats
Review queue 0
Prompts Shield flagged rather than blocked. Each one needs a decision.
Loading...
Recent prompts (all saved)
Loading...