Sieve: Local Secret Scanner for AI Coding Tool Chat Histories
Sieve is a macOS app that detects leaked secrets (API keys, tokens, passwords) from AI coding assistant chat histories. It targets a blind spot: while standard git scanners miss these local transcript stores, Sieve reads SQLite databases and plaintext files where agents record their actions.
What it scans
- Claude Code (~/.claude/)
- Cursor (Application Support/Cursor/)
- VS Code Copilot (Application Support/Code/)
- VS Code Insiders (Application Support/Code - Insiders/)
- Windsurf (Application Support/Windsurf/)
- Codex (~/.codex/)
- .env files in your project directories
Key features
- 100% local scanning — no network requests, no telemetry, no account required.
- Severity-based flagging of detected secrets.
- Redaction directly in VS Code SQLite chat databases (.vscdb), with timestamped backups before changes.
- Vault — new secret values stored in macOS Keychain, never exposed; copying requires Touch ID or login password.
- MCP integration — a local MCP server for Claude Code to check for exposed secrets, query findings, and run commands with vault-injected credentials without revealing raw secret values.
- Open source core (SieveCore).
Permissions model
Sieve uses macOS security-scoped bookmarks. On first launch, you grant read access to each tool's folder via a standard Open dialog. No further prompts after initial grant.
Practical concern
AI coding tools routinely read .env files as part of normal operation. Every secret they touch gets embedded in their local transcript/state files — unencrypted, outside .gitignore, persisted indefinitely. Sieve fills the gap that gitleaks and detect-secrets miss.
Available on the Mac App Store for $9.99. Requires macOS 13.0 or later. Size: 4 MB.
📖 Read the full source: HN AI Agents
👀 See Also
MCP Server CVE Exposure Mapping and Public API Released
Researchers have mapped CVE exposure across thousands of MCP servers and built a public API for querying dependency vulnerabilities. The API allows searching by repo/name, filtering by severity, and sorting by CVE count or recency.
Claude's Conversation Search Tool Still Returns Deleted Chats
A Claude Pro user discovered that deleted conversations remain retrievable through Claude's conversation search tool, returning substantive content including titles, message counts, and excerpts despite the chat links being dead.
Configuring OpenClaw for Encrypted LLM Inference Using TEE Enclaves
A developer shares how they configured OpenClaw to use Onera's AMD SEV-SNP trusted execution environments for end-to-end encrypted LLM inference, including configuration examples and technical tradeoffs.
pi-governance: RBAC, DLP, and audit logging for OpenClaw coding agents
pi-governance is a plugin that sits between AI coding agents and your system, classifying tool calls and blocking risky operations. It provides bash command blocking, DLP scanning for secrets and PII, role-based access control, and structured audit logging with zero configuration.