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 →

10,300

Skills Scanned (Live)

94

Avg Trust Score

44,750

Total Findings

9,179

Certified

Badge Distribution

CERTIFIED
9179 (89%)
CONDITIONAL
575 (6%)
SUSPICIOUS
271 (3%)
REJECTED
275 (3%)

Scan Sources

ClawHub Registry
6,208 (60%)
Public API● api
2,750 (27%)
Website Submit Page● website
1,339 (13%)
Admin
3 (0%)

1,339 skills submitted from the website

2,750 skills submitted via API clients

Most Common Findings

lowUnknown external reference20997×
lowNo explicit safety boundaries8672×
infoSafety boundaries defined1533×
infoError handling instructions present1409×
infoOutput constraints defined1399×
lowMissing or insufficient description1122×
mediumFinancial/payment actions detected749×
mediumSystem modification detected (inside code block)674×
mediumCapability contract mismatch: inferred network access is not declared626×
highCapability contract mismatch: inferred command execution is not declared562×