Cloak Env Protection

Trust Score 65/100

Prevents AI agents from leaking real .env secrets by using encrypted vaults and providing structurally valid sandbox values on disk.

triggers:protect .envsecret managementcloak initprevent secret leakenv security

GitHub SKILL.md

What it does

Cloak provides a security layer for environment variables, ensuring that AI coding agents only interact with fake 'sandbox' values while the human developer retains access to the real credentials via a secure vault and OS keychain integration.

When to use it

Use this skill in any project where you want to prevent an LLM from accidentally reading, logging, or exfiltrating production secrets from .env files.

What's included

Instructions: Provides strict rules for agents to identify Cloak presence via the .cloak file, prohibits direct editing of protected .env files, and mandates the use of cloak run for executing processes that require real secrets.
Tooling: Integrates with the Cloak CLI (Rust) and VS Code extension.

Compatible agents

Claude Code, Cursor, Windsurf, and other AI coding agents that follow project-root instruction files (CLAUDE.md, .cursorrules).

Audit Summary

Cloak is a skill for protecting .env secrets from AI coding agents by replacing on-disk values with sandbox fakes and providing a vault/CLI for real credential access. The SKILL.md is well-written with clear instructions, detection rules, and a command reference. Both bundled scripts failed in isolation — cross-compat-test.sh requires the extension/ directory context, and release.sh requires arguments plus a git repo. Security concern: SKILL.md includes `curl | sh` install instructions, which is a remote code execution pattern, though presented as user-facing rather than agent-autonomous.

Watch Out

curl | sh install pattern in SKILL.md is a security concern for supply-chain attacks
release.sh auto-pushes to origin/main without confirmation
Scripts require full repo context to run — won't work in isolation

Notes

The curl|sh pattern is instructional (for suggesting to developers) rather than something the agent executes autonomously, but still warrants the security deduction. The skill concept is genuinely useful and well-structured. Scripts are production-quality release tooling, not core skill functionality.

Information

Repository: Cloak
Stars: 25

Trust Score

Overall65

Security60

Code Quality72

Architecture65

Usefulness70

Related Skills

Reverse Engineer

Provides step-by-step guidance and best practices for binary reverse engineering: static analysis, dynamic tracing, disassembly, and documentation workflows for

Sandbox0 Integration

Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.

Websocket Client Creator

Generates and guides websocket client integrations: configuration, code samples, best practices, and validation for production-ready websocket clients.

CTF Write-up Generator

Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.

Azure External Attack Surface Management

Provides expert guidance for Azure External Attack Surface Management (EASM): quotas, configuration, integrations, and exporting inventory to analytics platform

Node.js Best Practices

Guidelines and decision-making for Node.js architecture, runtime, async patterns, security, validation, and testing to inform framework and system choices.

radar — Smart Contract AST & Security Analysis

Multi-framework AST generator and static analysis tool for smart contracts (Rust/Anchor/Stylus and Solidity/Foundry) with a template DSL for writing detection r

Bash Pro

Defensive, production-grade Bash scripting patterns and CI/CD best practices: strict mode, safe argument parsing, testing with Bats, and tooling (ShellCheck/shf

Back to Skills