Skill Security Audit Service
Five-tier Audit · Six-dimension Analysis · LLM Review
Audit a Skill
Enter a ClawHub or GitHub skill URL to check for security issues
-
Total Audits
-
Safe
-
Suspicious
-
Malicious
Audited Skills
0
requests today
Skill
Author
Result
Risk Score
Downloads
Five-tier Detection
Core Rules → Dynamic Rules → LLM Analysis → Sandbox → LLM Review
Sandbox Execution
Firecracker microVM isolation for safe dynamic analysis
Rule Evolution
Continuous learning of new attack patterns with automatic rule promotion
SAFE
0.2
Risk
Detected Threats
LLM Semantic Analysis
Inferred Intent
-
Risk Factors
Recommendation
-
Sandbox Execution
Security Behavior
Performance Metrics
Details
Audit Analytics
Real-time statistics, trends, and recent audit activity
-
Total Audits
-
Safe
-
Suspicious
-
Malicious
7-Day Audit Trend
Last 7 daysThreat Distribution
All timeRecent Audits
Latest 10
Skill
Source
Result
Time
API
Documentation
Integrate ClawSec skill security auditing into your agent or workflow
Base URL
https://api.clawsec.cc
Authentication
All requests require X-API-Key header
Browser
GitHub OAuth → key auto-saved
Agent
Device Flow →
/register → /verify
Rate Limits
100
requests / week
5 min
max audit time
Resets every Monday. All requests count toward quota.
Endpoints
Audit
POST
/api/v1/audit
Five-tier six-dimension security audit
GET
/api/v1/skills
List audited skills (paginated, max 50)
GET
/api/v1/stats
Audit statistics and trends
Authentication
POST
/api/v1/api-keys/register
Start GitHub Device Flow
POST
/api/v1/api-keys/verify
Poll for API key
Intelligence
POST
/api/v1/feedback
Submit TP/FP feedback
POST
/api/v1/intel/submit
Submit threat intelligence
GET
/api/v1/attack/technique/{id}
MITRE ATT&CK lookup
Contact
Get in Touch
Questions, feedback, or partnership inquiries about ClawSec skill security audit service.
huacheng99@gmail.com