Is your AI skill safe?

Paste any GitHub repo. Get a trust score across 12 signals — including safety scans for prompt injection, credential theft, and supply chain attacks.

1,184 malicious skills found in ClawHavoc 36% of ClawHub skills had prompt injection 12 trust signals scored
Try: modelcontextprotocol/servers · anthropics/anthropic-sdk-typescript · vercel/ai

Every repo scored across 4 dimensions, 12 signals, mapped to trust tiers.

✅
Verified
Active maintenance, strong docs, real adoption, secure. Build on this with confidence.
🟡
Established
Solid choice with caveats. Check the details before depending on it.
🔵
New
Promising but unproven. Use with awareness.

Simple pricing

Free trust tier for every scan. Pay only when you want the full picture.

Free
$0
forever
  • Trust tier badge
  • Dimension scores
  • One-line rationale
  • Unlimited scans
Full Report
$9
per report
  • All 12 signal scores
  • Safety scan findings
  • Skills Mode analysis
  • Shareable report URL
10-Pack
$29
$2.90 per scan
  • 10 full reports
  • Audit your whole stack
  • Same full analysis
  • Never expires