Live data

AI Agent Security Index

Every scan contributes anonymous threat data. See what the community is finding.

Privacy & Data Collection

What we collect (anonymized)

  • Finding categories detected
  • Severity counts (critical / high / medium / low)
  • Platform type (Claude Code, Cursor, MCP, etc.)
  • Security grade (A through F)
  • Week of scan (no timestamp)

What we never collect

  • Source code or file contents
  • File paths or directory names
  • API keys, credentials, or secrets
  • User identifiers or IP addresses
  • Project names or repository URLs

Add your stack to the index

Every scan contributes anonymous finding data. No code or file paths shared.

npx firmis-cli init

Then run firmis scan - no account required. View on GitHub ↗