Screening Process
Every skill on AgentSource goes through a multi-layer verification pipeline before it reaches your agent. No exceptions.
4 Layers of Verification
Static Analysis
Automated code scanning for vulnerabilities, malicious patterns, and dependency risks. We check for command injection, data exfiltration, excessive permissions, and known CVEs in dependencies.
- Dependency vulnerability scan
- Malicious pattern detection
- Permission scope validation
- License compatibility check
Sandboxed Execution
Every skill runs in an isolated sandbox with network restrictions. We probe each tool with test inputs, verify outputs match declared schemas, and measure performance characteristics.
- Tool input/output validation
- Response time benchmarking
- Memory and CPU profiling
- Error handling verification
Permission Audit
Declared permissions are verified against actual behavior. If a skill declares no network access but attempts outbound connections, it fails. What you declare is what you get.
- Network access verification
- Filesystem access boundaries
- Resource usage limits
- Undeclared behavior detection
Ongoing Monitoring
After listing, skills are continuously monitored. Health checks every 5 minutes, trust scores update in real-time based on uptime, success rate, call volume, and user reports.
- 5-minute health probes
- Real-time trust score updates
- Anomaly detection
- User report investigation
Trust Score
Every skill earns a trust score from 0 to 100 based on real metrics — not self-reported claims. The score is a weighted composite of:
| Factor | Weight | Description |
|---|---|---|
| Uptime (30d) | 25% | Percentage of successful health checks in the last 30 days |
| Success Rate | 25% | Percentage of non-error responses to tool calls |
| Screening Score | 20% | Score from the initial screening pipeline |
| Call Volume | 15% | Total number of calls (higher volume = more proven) |
| Author Reputation | 10% | Based on all skills by the same creator |
| Age | 5% | Time since first published (maturity bonus) |
What Gets Rejected
Skills are rejected or delisted for:
- ✕Malicious code or data exfiltration attempts
- ✕Undeclared permissions (e.g., secret network calls)
- ✕Persistent test failures or unreliable behavior
- ✕Known vulnerable dependencies without patches
- ✕Excessive resource consumption beyond declared needs
- ✕Deceptive descriptions that don't match actual functionality
38.8% of MCP skills on open registries have security flaws.
0% of AgentSource skills do.