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 →

10,239

Skills Scanned (Live)

96

Avg Trust Score

45,335

Total Findings

9,408

Certified

Badge Distribution

CERTIFIED
9408 (92%)
CONDITIONAL
489 (5%)
SUSPICIOUS
73 (1%)
REJECTED
269 (3%)

Scan Sources

ClawHub Registry
6,677 (65%)
Public API● api
2,497 (24%)
Website Submit Page● website
1,062 (10%)
Admin
3 (0%)

1,062 skills submitted from the website

2,497 skills submitted via API clients

Most Common Findings

lowUnknown external reference24977×
lowNo explicit safety boundaries8737×
infoSafety boundaries defined1494×
infoError handling instructions present1412×
infoOutput constraints defined1378×
lowMissing or insufficient description1138×
mediumFinancial/payment actions detected749×
mediumSystem modification detected (inside code block)671×
infoMany external URLs referenced (6)242×
highEnvironment variable access + network send (credential harvesting)229×