Skip to main content
skill CX Codex

skill-security-auditor · borghei — Claude Code skill for auditing agent skills

skill-security-auditor — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode that scans agent skills before install. It detects prompt injection, dangerous code, credential harvesting and supply chain risks.

LicenseRef-MIT-Commons-Clause 146 installs ★ 1,183 updated 2026-11-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add borghei/Claude-Skills --skill skill-security-auditor -a claude-code
Open on GitHub

What skill-security-auditor does

Python files are checked for risky patterns: os.system, subprocess with shell=True, eval/exec, obfuscation via base64 or chr(), network exfiltration, reads from ~/.ssh or ~/.aws. Markdown, text and YAML get scanned for prompt injection: system-prompt overrides, zero-width characters, HTML comments with hidden instructions, and prompts that tell the assistant to conceal actions.

A separate checker looks at dependencies. Typosquatted package names (reqeusts), unpinned versions in requirements*.txt and package.json, inline pip/npm install calls. Pinned versions are not checked against CVE feeds; run pip-audit, npm audit or OSV-Scanner for that.

Each of the three scripts returns PASS / WARN / FAIL. PASS means "nothing obvious found", not "safe": the scanners match regexes line by line, and string building or helper indirection defeats them. After a PASS on an untrusted skill, read the code yourself.

What it helps with

  • scan a skill before installing it from an untrusted source
  • catch hidden instructions in markdown and YAML
  • detect reads of SSH keys or AWS credentials
  • spot typosquatted packages and unpinned dependency versions
  • gate skill installs in CI/CD

Example prompts for the agent

  • Scan assets/sample_malicious_skill/ with all three checkers
  • Run python scripts/code_scanner.py skills/ --strict --json and show HIGH findings only
  • Check requirements.txt for unpinned versions and typosquatted package names

How to install skill-security-auditor

1Skills CLI (Vercel)

npx skills add borghei/Claude-Skills --skill skill-security-auditor -a claude-code

2Manually: put the files in place

~/.claude/skills/skill-security-auditor/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/skill-security-auditor/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about skill-security-auditor

How do I install skill-security-auditor in Claude Code?

Run npx skills add borghei/Claude-Skills --skill skill-security-auditor -a claude-code. The skill file lands at ~/.claude/skills/skill-security-auditor/SKILL.md.

What does skill-security-auditor do?

It runs static analysis on agent skills before install: dangerous constructs in Python, prompt injection in markdown and YAML, and dependency issues. The output is a PASS / WARN / FAIL verdict with findings grouped by severity and remediation notes.

Does PASS mean the skill is safe?

No. The scanners match regular expressions line by line and only catch common, unobfuscated attack forms. String concatenation, encoding and indirection through helpers evade them. For an untrusted skill, read the scripts yourself even after a PASS.

Similar skills

All skills for Security →

skill-security-auditor by other authors comes first.

skill-security-auditor Alireza Rezvani skill-security-auditor scans AI agent skills for malicious code before install: detects eval(), os.system(), data exfiltration, prompt injection, and vulnerable dependencies. CX Codex +1 785installs skill-scanner getsentry skill-scanner — a skill for Claude Code and Codex checks agent skills for injection, unsafe code, excess permissions, and secret exposure. It returns findings for review. CX Codex +1 4,200installs mcp-security-audit official github mcp-security-audit scans .mcp.json files for hardcoded secrets, shell injection patterns, and unpinned package dependencies. Runs before commits or when onboarding new MCP servers to a repository. CX Codex +1 1,100installs dfyx-code-security-auditor reason-machines dfyx-code-security-auditor is a Claude Code skill that traces data flows and checks security weaknesses in release reviews and OWASP assessments. CX Codex +1 338installs ai-agent-security devops-skills ai-agent-security — a skill for defending agents against prompt injection, tool abuse and data exfiltration. Useful when an agent touches production, databases or cloud accounts. CX Codex +1 389installs repo-security-posture superagent-ai repo-security-posture audits a GitHub repository and CI/CD workflows for hardening gaps, delivering a ranked checklist of security fixes mapped to real attack scenarios. CX Codex +1 876installs llm-app-security devops-skills llm-app-security is a Claude Code skill with security controls and validation rules to protect chatbots, RAG pipelines, and SaaS AI features from prompt injection, leaks, and abuse. CX Codex +1 365installs

From the same set120

The whole set →
agent-designer agent-designer — a skill for Claude Code and related platforms that plans multi-agent architectures. It generates tool definitions for Anthropic and OpenAI, diagrams communication flows, and parses runtime logs. CX Codex +1 161installs marketing-psychology The marketing-psychology skill uses behavioral psychology and mental models to diagnose marketing friction. Use it for landing pages, pricing, email, ads, and conversion work. CX Codex +1 151installs aws-solution-architect aws-solution-architect — a skill for Claude Code, Codex, and Cursor that designs AWS architectures and outputs IaC templates. Tailors cloud patterns to workload demands and flags infrastructure savings. CX Codex +1 150installs playwright-pro playwright-pro — a skill for Claude Code, Codex, and Cursor. Generates Playwright end-to-end tests, builds Page Object structures, diagnoses flaky runs, and migrates suites from Cypress or Selenium. CX Codex +1 148installs create-prd create-prd builds a product requirements doc in eight parts, from problem statement to P0/P1/P2 scope and release plan. Useful when a new feature needs one shared spec. CX Codex +1 146installs senior-computer-vision senior-computer-vision is a Claude Code skill for designing computer vision pipelines with object detection and segmentation. CX Codex +1 145installs app-store-optimization app-store-optimization is a Claude Code skill that researches store keywords, refines app metadata, and analyzes reviews for Apple App Store and Google Play listings. CX Codex +1 144installs tdd-guide The tdd-guide Claude Code skill guides red-green-refactor cycles and works with test suites. It can draft tests from requirements and inspect coverage reports for gaps. CX Codex +1 143installs

Project sponsors

Companies that keep this analytics open