skills.rest
giuseppecutuli
giuseppecutuliCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

security-scan

Scans Claude Code projects for misconfigs and vulnerabilities.

Updated Aug 23, 2026
Search Tags:#security#claude#compliance#configuration#vulnerabilities#scan#agentshield
One-click install
npx skills add https://github.com/giuseppecutuli/speakdoc --skill security-scan-giuseppecutuli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/giuseppecutuli/speakdoc/tree/main/.claude/skills/security-scan
Command: npx skills add https://github.com/giuseppecutuli/speakdoc --skill security-scan-giuseppecutuli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Claude Code configurations can harbor security vulnerabilities and misconfigurations that expose secrets or enable prompt injection; this skill provides automated auditing to surface issues before they cause harm.

Core Features & Use Cases

  • Scans CLAUDE.md, settings.json, MCP configs, and hooks for risky patterns and misconfigurations.
  • Reports findings with severity grades and actionable remediation guidance.
  • Integrates with CI/CD and supports secure export formats for audits.

Quick Start

Run AgentShield against your Claude Code project to generate a secure baseline.

Frequently Asked Questions about security-scan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scan Claude Code configurations for security vulnerabilities?▼

AgentShield audits CLAUDE.md, settings.json, MCP configs, and hooks to surface security vulnerabilities, hardcoded secrets, and risky permissions, providing actionable remediation guidance with severity grades.

What types of misconfigurations can AgentShield detect in Claude Code?▼

AgentShield detects hardcoded secrets, prompt injections, and risky permissions by scanning CLAUDE.md, settings.json, MCP configs, hooks, and agent definitions for risky patterns and misconfigurations.

Do I need to install AgentShield to audit my Claude Code settings?▼

Yes, AgentShield installation is required to use this skill for auditing Claude Code configurations, generating reports, and applying optional auto-fixes for detected vulnerabilities.

Can I export Claude Code security audit results to JSON or HTML?▼

You can export audit results to terminal, JSON, Markdown, or HTML formats, supporting CI/CD integration and secure exports for compliance audits.

How do I fix prompt injection risks in CLAUDE.md files?▼

Use the optional auto-fix feature after scanning to remediate detected prompt injection risks, receiving actionable integration guidance to secure your CLAUDE.md files.

Does this security scan work for existing repositories or only new projects?▼

The scan is applicable to both new and existing repositories, auditing Claude Code configurations to surface vulnerabilities and misconfigurations across all project states.

Related Skills

Explore More Software Engineering Skills→
mitul-bhatiamitul-bhatia

security-scan

Audit Claude Code configurations for security vulnerabilities using AgentShield.

Community
Intermediate
hopeoverturehopeoverture
6

a11y-checker-ci

Automate WCAG accessibility checks in CI/CD pipelines and generate PR reports.

Community
Advanced
SensLiaoSensLiao

security-remediation

Automate security finding remediation with regression tests and evidence generation.

Community
Advanced
SergeiGolosSergeiGolos
1

vulnerability-scanner

Detect and prioritize security vulnerabilities across dependencies, secrets, code patterns, and configurations.

Community
Advanced