Find and prevent secrets and prompt injection attacks in AI coding agent sessions
Security incident alerts for your whole stack
Stage
Not given
Startup
Founded
Not given
Not given
Based in
Not given
GB
Pricing model
Open source
Freemium
Pricing
Not given
Solo $12/month for up to 10 projects with 1 member; Team $49/month for up to 25 projects with unlimited members; Business $199/month for up to 150 projects with unlimited members and priority support. Free 7-day trial with no card required.
Key features
Scan recorded AI agent sessions for known credentials
Guard against prompt injection attacks
Local console with audit trails at 127.0.0.1
Support for multiple AI coding agents including Claude Code, Cursor, and Codex CLI
Default policy with 21 rules across 19 action classes
Test policy against replayed attack scenarios
No model or network in the guard's hot path
Inventory of packages, container images, GitHub Actions, runtimes and cloud services
Real-time incident alerts across OSV.dev, GitHub Advisory, CISA KEV and security news
Local machine checks without reading source code or secrets
GitHub Action for pull request checks and inventory updates
Support for 50+ third-party services including Stripe, OpenAI, Vercel and Supabase
Signed notices with Ed25519 to verify authenticity
What makes it different
Deterministic policy-based enforcement rather than model-based decisions
Runs locally with no telemetry and no account required
Open source and free forever under Apache-2.0
Replayed 36 real attack scenarios with zero bypasses
Scans run on your machine; source code and file contents never leave it
Checks new incidents every 5 minutes against your entire stack across all layers
Works alongside dependency scanners to monitor already-running components
Free checks and public notices available without account or subscription