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 →

10,301

Skills Scanned (Live)

94

Avg Trust Score

44,768

Total Findings

9,178

Certified

Badge Distribution

CERTIFIED
9178 (89%)
CONDITIONAL
577 (6%)
SUSPICIOUS
270 (3%)
REJECTED
276 (3%)

Scan Sources

ClawHub Registry
6,206 (60%)
Public API● api
2,749 (27%)
Website Submit Page● website
1,343 (13%)
Admin
3 (0%)

1,343 skills submitted from the website

2,749 skills submitted via API clients

Most Common Findings

lowUnknown external reference20981×
lowNo explicit safety boundaries8670×
infoSafety boundaries defined1535×
infoError handling instructions present1408×
infoOutput constraints defined1399×
lowMissing or insufficient description1122×
mediumFinancial/payment actions detected748×
mediumSystem modification detected (inside code block)675×
mediumCapability contract mismatch: inferred network access is not declared631×
highCapability contract mismatch: inferred command execution is not declared567×