Agent Secrets Scanner – Check AI sessions for leaked keys

Find accidentally pasted secrets in Claude Code, Codex, and Cursor sessions

Problem

Developers routinely paste API keys, DB passwords, and private tokens into AI coding sessions. These linger in local session history and leak the moment sessions are shared, logs exported, or devices change. There's no unified scanner across tools.

Solution

A local CLI / menu bar tool that reads local session stores of common agents like Claude Code, Codex, and Cursor, detects suspected secrets using configurable pattern matching plus entropy checks, and reports the session, context, and suggested rotation or redaction.

Users

Developers using multiple AI coding agents, security-conscious teams, and engineering orgs with compliance needs

MVP

Scan local session directories of major coding agents; built-in regex patterns for common keys (OpenAI/AWS/GitHub, etc.) plus entropy detection; report suspicious entries with context; one-click redaction or cleaned export; offline and local-only

Revenue

Free local version plus team subscription (policy distribution, audit logs, CI pre-commit hooks).

Why now

AI coding sessions have become a new accumulation point for sensitive data with no dedicated scanner. Rising anxiety around key leaks lets indie devs ship a practical local-first tool fast.