Skip to content
@dotsetlabs

Dotset Labs

Runtime Secret Protection

Dotset Labs

Open-source security tools for the AI era.

Website Documentation License


Defense in Depth for AI Development

AI assistants create new attack surfaces. Our tools provide layered security across the development lifecycle:

Stage Tool Purpose
Pre-install Hardpoint Scan your dev environment for hidden threats
At Runtime Tollgate Enforce policies on AI agent actions
Detection Deadfall Detect AI compromise with cognitive honeypots

Hardpoint

Developer environment security scanner for the AI era.

Hardpoint scans your development environment for threats that traditional security tools miss — malicious AI config files, prompt injection, hidden Unicode, and more.

GitHub

# Install
go install github.com/dotsetlabs/hardpoint/cmd/hardpoint@latest

# Scan your environment
hardpoint scan

# Auto-fix certain issues
hardpoint fix AI-003 CLAUDE.md

# Manage suppression baselines
hardpoint baseline list
hardpoint baseline add AI-001 --reason "Known safe"

Key Features

Feature Description
AI Config Scanner Detects threats in .cursorrules, CLAUDE.md, mcp.json
Hidden Unicode Finds invisible characters that can hide malicious instructions
Prompt Injection Identifies attempts to override AI assistant behavior
Shell Backdoors Scans .bashrc, .zshrc for suspicious commands
Git Hook Analysis Checks for malicious git hooks
SARIF Output GitHub Code Scanning integration

Tollgate

Policy-based security proxy for MCP (Model Context Protocol) servers.

Tollgate sits between AI agents and MCP servers, enforcing security policies before any tool is executed.

npm GitHub

npm install -g @dotsetlabs/tollgate

# Wrap any MCP server with protection
tollgate wrap npx @anthropic/mcp-server-fs ./

# Or use a config file for custom policies
tollgate start --server postgres

Key Features

Feature Description
Policy Engine Allow, deny, or prompt based on tool, arguments, and risk level
Risk Analysis Smart analyzers for SQL, Filesystem, Shell, and HTTP API calls
Server Scanner Scan any MCP server to discover tools and assess risks before use
Templates Growing collection of policy templates for popular MCP servers
Audit Logging Every tool invocation logged to SQLite with PII redaction
Compliance Export logs in JSON, JSONL, CSV, or CEF formats
Approval Methods Terminal prompts, interactive web UI, or webhook integration

Works With

  • Claude Desktop
  • Cursor
  • Claude Code
  • Any MCP-compatible AI agent

Deadfall

Cognitive honeypots for AI agent detection.

Deadfall detects AI agent compromise by exploiting their instruction-following behavior. Trapped files instruct agents to call a verification tool — which triggers an alert.

GitHub

# Install
go install github.com/dotsetlabs/deadfall/cmd/deadfall@latest

# Initialize in your project
deadfall init

# Create trap files
deadfall trap cursor-rules      # .cursorrules for Cursor
deadfall trap claude-context    # CLAUDE.md for Claude
deadfall trap mcp-config        # mcp.json honeypot

# Verify your setup
deadfall test

# Start the Honey-MCP server
deadfall serve

Key Features

Feature Description
Cognitive Traps Exploit AI instruction-following to detect compromise
AI-Specific Types Traps for Cursor, Claude, Copilot, MCP clients
Honey-MCP Server Honeypot tools that attract malicious agents
Token Correlation Alerts include which file was read
Multi-Channel Alerts Desktop, log file, webhook delivery

Trust & Security

Your data never leaves your machine. All Dotset Labs tools are 100% local — no cloud, no telemetry, no account required.


Links

Built for developers working with AI.

Popular repositories Loading

  1. .github .github Public

  2. mintlify-docs mintlify-docs Public

    MDX

  3. tollgate tollgate Public

    Local-first MCP security proxy with policy-based access control for AI agents. Human-in-the-loop approvals, smart content analysis, prompt injection protection, and audit logging. Works with Claude…

    TypeScript 1

  4. hardpoint hardpoint Public

    Security scanner purpose-built for developers using AI coding assistants. Detects prompt injection in .cursorrules/CLAUDE.md, Trojan Source attacks, MCP command injection, shell backdoors, and expo…

    Go

  5. deadfall deadfall Public

    AI agent honeypot and canary token generator. Create fake credentials, API keys, and MCP tools to detect when AI agents or intruders access sensitive resources. Tripwires for your development envir…

    Go

Repositories

Showing 5 of 5 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…