Skip to content
System Telemetry

Scanning Statistics

Real-time transparency into the state of AI agent skill security.

Looking for the snapshot research report? Read the Intelligence Report →

10,295

Skills Scanned (Live)

94

Avg Trust Score

44,679

Total Findings

9,184

Certified

Badge Distribution

CERTIFIED
9184 (89%)
CONDITIONAL
568 (6%)
SUSPICIOUS
269 (3%)
REJECTED
274 (3%)

Scan Sources

ClawHub Registry
6,223 (60%)
Public API● api
2,742 (27%)
Website Submit Page● website
1,327 (13%)
Admin
3 (0%)

1,327 skills submitted from the website

2,742 skills submitted via API clients

Most Common Findings

lowUnknown external reference21017×
lowNo explicit safety boundaries8676×
infoSafety boundaries defined1528×
infoError handling instructions present1407×
infoOutput constraints defined1400×
lowMissing or insufficient description1122×
mediumFinancial/payment actions detected748×
mediumSystem modification detected (inside code block)674×
mediumCapability contract mismatch: inferred network access is not declared607×
highCapability contract mismatch: inferred command execution is not declared552×