deepsafe-scan

Community

Preflight security for AI agent environments.

AuthorXiaoYiWeio
Version1.0.0
Installs0

System Documentation

What problem does it solve?

DeepSafe Scan provides a preflight security check for AI coding agents by examining deployment/posture configs, installed Skills and MCP servers, memory/sessions, and agent hook configurations for secrets, PII, prompt injections, and backdoors, enabling safer AI workflows.

Core Features & Use Cases

  • Static posture, memory, and hooks analysis across multiple agent platforms to reveal misconfigurations and credential exposure.
  • Static scanning of skills/MCP directories to detect hardcoded secrets, dangerous calls, and data exfiltration patterns, with optional LLM-assisted semantic analysis.
  • Memory/session review for secrets and PII leakage, plus prompts-injection risk assessment.
  • Hooks/delivery configuration analysis to identify potential backdoors or prompt-injection vectors.
  • Cross-platform compatibility: OpenClaw, Claude Code, Cursor, Codex, and OpenCode integration.

Quick Start

Run the scanner on your project to generate a comprehensive security report.

Dependency Matrix

Required Modules

python3

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: deepsafe-scan
Download link: https://github.com/XiaoYiWeio/deepsafe-scan/archive/main.zip#deepsafe-scan

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.