hardstop

What problem does it solve?

This Skill prevents AI-driven or user-initiated shell commands and file reads from causing harm by enforcing a pre-execution safety protocol and guarding against credential exposure.

Core Features & Use Cases

• Pre-execution protocol: Instant block checks, risk assessment, signal of confidence, and explicit confirmation for risky actions before execution.
• Credential read protection: Blocks reading of sensitive files like ~/.ssh, ~/.aws, ~/.env, and other credentials sources.
• LLM-awareness for non-hook environments: Provides safety guidance when no deterministic hooks are available.
• Transparent rationale and logs: Shares why a command is blocked or allowed to help user understanding.

Quick Start

Instruct the skill to review commands before execution, for example: "Please evaluate the following shell command: rm -rf ~/" and respond with whether to block or allow.