Scan Claude Code configurations for security vulnerabilities and misconfigurations.
npx skills add https://github.com/kouiso/designdiff --skill security-scan-kouiso
Please help me install this Agent Skill. Skill: security-scan Source: https://github.com/kouiso/designdiff/tree/main/.claude/skills/security-scan Command: npx skills add https://github.com/kouiso/designdiff --skill security-scan-kouiso
This Skill identifies and helps fix security vulnerabilities, misconfigurations, and potential injection risks within your Claude Code project's configuration files and agent definitions.
CLAUDE.md, settings.json, MCP configurations, hooks, and agent definitions for security flaws.Run a security scan on your current project's .claude directory.
High-intent search queries and answers about installing and using this skill.
Scanning Claude Code configurations for security vulnerabilities involves checking files like CLAUDE.md, settings.json, and MCP servers for hardcoded secrets, prompt injection, and excessive permissions. This Skill uses AgentShield to detect and report these misconfigurations so you can harden your project setup.
Prompt injection in Claude Code agent definitions involves malicious instructions hidden in config files that manipulate agent behavior. This Skill detects these injection patterns and other supply chain risks across your CLAUDE.md and MCP configurations to prevent unauthorized actions.
Yes, you need AgentShield installed or available via npx to scan settings.json and MCP configurations. The Skill relies on AgentShield to perform the vulnerability checks that identify hardcoded secrets and excessive permissions in your Claude Code project.
The best way to harden Claude Code hooks against misconfigurations is to run a comprehensive security scan before deployment. This Skill analyzes your hooks and agent definitions, flagging overly permissive access and supply chain risks so you can fix them.
A Claude Code security scan reports excessive permissions when your settings.json or MCP server configurations grant broader access than necessary. The Skill identifies these overly permissive settings to help you restrict access and prevent potential misuse.
RUSHYOPScan Claude Code configurations for security vulnerabilities using AgentShield.
EojEdredScan code and configurations for security vulnerabilities and replay risks.
j4hr3nAudit MCP server implementations for security risks and misconfigurations.
ZESCODEScan Claude Code configuration files for secrets and misconfigurations.