Audit Claude Code configurations for security issues and misconfigurations.
npx skills add https://github.com/vinwang/tools --skill security-scan-vinwang
Please help me install this Agent Skill. Skill: security-scan Source: https://github.com/vinwang/tools/tree/main/iflow/skills/security-scan Command: npx skills add https://github.com/vinwang/tools --skill security-scan-vinwang
Audit Claude Code configurations for security issues, misconfigurations, and prompt injection vulnerabilities using AgentShield.
Run a quick audit by installing AgentShield and scanning the project directory.
High-intent search queries and answers about installing and using this skill.
To scan Claude Code configurations for security vulnerabilities, install AgentShield and run a project directory audit to detect hardcoded secrets, prompt injection patterns, and risky settings. It checks CLAUDE.md, settings.json, mcp.json, hooks/, and agent definitions.
AgentShield security scanning detects hardcoded secrets, prompt injection patterns, and risky configurations in MCP servers, hooks, settings.json, and agent definitions. It identifies insecure setups across CLAUDE.md and mcp.json files to maintain project security hygiene.
Yes, you need AgentShield installed to audit your Claude Code project. The security scan requires AgentShield to evaluate CLAUDE.md, settings.json, mcp.json, hooks, and agent files for misconfigurations and prompt injection vulnerabilities.
You should perform a Claude Code security audit when setting up a new project, updating CLAUDE.md or settings.json, modifying MCP configurations, or conducting periodic security hygiene checks across your repositories.
Yes, you can auto-fix Claude Code security issues found during a scan. The security scanning process supports an auto-fix option to resolve detected misconfigurations and vulnerabilities across your configuration files and agent definitions.
Scanning Claude Code configurations supports various output formats for the security audit results. The scan generates reports detailing detected vulnerabilities, prompt injection patterns, and misconfigurations found in your CLAUDE.md, settings.json, and MCP files.
firstsun-devAudit Claude Code configurations for security weaknesses and misconfigurations.
cosmixIdentify vulnerabilities, misconfigurations, and security best-practice violations across code, configurations, and infrastructure.
TECHKNOWMAD-LABSScan code repositories for vulnerabilities and leaked secrets using static analysis tools.
MomoDavilukeScan Claude Code configurations for vulnerabilities and misconfigurations using AgentShield.
