On-device Chrome extension that blocks credential leaks to LLM chats
Local neural network catches leaks in 150ms with zero telemetry.
Detection tells you a key is real; geiger tells you whether it's dangerous.
Read-only recon for leaked creds tells you impact before you rotate everything.
Security engineers, incident responders, DevOps teams
Prowler · ScoutSuite · TruffleHog
Local neural network catches leaks in 150ms with zero telemetry.
Solid security research, but it's a case study—not a tool you can actually use.
Yet another secret scanner, but this one's a single Python file.
Pass integration for Git, but git-credential-store and libsecret do this.
Agents never touch raw tokens — you swap literal credentials for template variables and a proxy injects scoped secrets server-side while surfacing one‑click approval links to humans. It also fingerprints machines, uses SSH key auth, and tries to infer minimal OAuth scopes per request, which is a neat user-in-the-loop model. The obvious trade-off is centralizing trust in the proxy and the integration work for every provider, but the UX for human approvals and instant revocation is compelling.
Deterministic Terraform risk scorer beats AI guessing for deploy safety.