deepsafe-scan

Name: XiaoYiWeio/deepsafe-scan
Author: XiaoYiWeio

Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors in .cursorrules, CLAUDE.md, AGENTS.md and more.

Subagents72 stars10 forks● PythonUpdated 14d ago

ClaudeWave Trust Score

62/100

· OK

Passed

✓Actively maintained (<30d)
✓Clear description
✓Topics declared

Flags

!No standard license detected

Last scanned: 6/11/2026

Install as a Claude Code subagent

Method: Clone

Terminal

git clone https://github.com/XiaoYiWeio/deepsafe-scan && cp deepsafe-scan/*.md ~/.claude/agents/

1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).

2. Start a new Claude Code session to load the agents.

3. Delegate work to them with the Task/Agent tool or by name.

Installable items

1 items in this repository

deepsafe-scanSkill

Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced semantic analysis. Works with OpenClaw, Claude Code, Cursor, Codex, and OpenCode. Use when a user asks for a security audit, health check, or wants to scan their AI agent setup for vulnerabilities.

Install

Use cases

Security AI / ML

About

Subagents overview

README preview not available. Visit the repo on GitHub for full documentation.

Topics

ai-agentsaisecurityclaudeclaude-codecodexcursoropenclawopenclaw-pluginopenclaw-skillopenclaw-skillsprompt-injectionprompt-injection-llm-securitysafety

Frequently asked

What people ask about deepsafe-scan

What is XiaoYiWeio/deepsafe-scan?

XiaoYiWeio/deepsafe-scan is subagents for the Claude AI ecosystem. Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors in .cursorrules, CLAUDE.md, AGENTS.md and more. It has 72 GitHub stars and was last updated 14d ago.

How do I install deepsafe-scan?

You can install deepsafe-scan by cloning the repository (https://github.com/XiaoYiWeio/deepsafe-scan) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is XiaoYiWeio/deepsafe-scan safe to use?

Our security agent has analyzed XiaoYiWeio/deepsafe-scan and assigned a Trust Score of 62/100 (tier: OK). See the full breakdown of passed checks and flags on this page.

Who maintains XiaoYiWeio/deepsafe-scan?

XiaoYiWeio/deepsafe-scan is maintained by XiaoYiWeio. The last recorded GitHub activity is from 14d ago, with 0 open issues.

Are there alternatives to deepsafe-scan?

Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.

1-click deploy

Deploy deepsafe-scan to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Vercel Railway Render

Embeddable badge

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Markdown (README)

[![Featured on ClaudeWave](https://claudewave.com/api/badge/xiaoyiweio-deepsafe-scan)](https://claudewave.com/repo/xiaoyiweio-deepsafe-scan)

HTML

<a href="https://claudewave.com/repo/xiaoyiweio-deepsafe-scan"><img src="https://claudewave.com/api/badge/xiaoyiweio-deepsafe-scan" alt="Featured on ClaudeWave: XiaoYiWeio/deepsafe-scan" width="320" height="64" /></a>

More Subagents

affaan-m

ECC

yesterday

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

214.4k32.9kJavaScript

Subagentsai-agentsanthropicInstall