Statically review a Claude Code / AI-agent setup for security misconfigurations — risky hooks, over-broad permissions, untrusted or cleartext MCP servers, hardcoded secrets, endpoint redirection, over-privileged agents/skills, and prompt-injection in steering files. Use when asked to audit a .claude/ directory, settings.json, .mcp.json, a plugin/marketplace, or CLAUDE.md, or to add a config-security gate to CI. Drives the agentscanner CLI.
$npx -y skills add jassics/awesome-claude-security --skill config-security-scanInstalls into the current project.
Run `npx skills use "https://github.com/jassics/awesome-claude-security" --skill "jassics/awesome-claude-security/config-security-scan"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/jassics/awesome-claude-security" that are relevant to the current task. Run `npx skills add "https://github.com/jassics/awesome-claude-security"` and select the relevant skills, then follow their instructions.