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 →
Resume your workflow
We saved your last report and scan target so you can jump from telemetry back into the active trust workflow.
10,342
Skills Scanned (Live)
94
Avg Trust Score
45,167
Total Findings
9,191
Certified
Badge Distribution
CERTIFIED
9191 (89%)
CONDITIONAL
598 (6%)
SUSPICIOUS
273 (3%)
REJECTED
280 (3%)
Scan Sources
ClawHub Registry
6,206 (60%)
Public API● api
2,809 (27%)
Website Submit Page● website
1,324 (13%)
Admin
3 (0%)
1,324 skills submitted from the website
2,809 skills submitted via API clients
Most Common Findings
lowUnknown external reference21117×
lowNo explicit safety boundaries8700×
infoSafety boundaries defined1546×
infoError handling instructions present1413×
infoOutput constraints defined1395×
lowMissing or insufficient description1152×
mediumFinancial/payment actions detected749×
mediumSystem modification detected (inside code block)681×
mediumCapability contract mismatch: inferred network access is not declared671×
highCapability contract mismatch: inferred command execution is not declared584×