Skip to content
TrustedSkillsbeta
Back to all skills

Security Audit

Listed
netresearch·vlatest·security

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 netresearch/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

netresearch

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 3 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 5 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: 169.254.169.254, attacker.com, evil.com, payment-provider.com, victim.com.

    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

    169.254.169.254undeclaredpayment-provider.comundeclaredwww.w3.orgstandardsvictim.comundeclaredevil.comundeclaredmetadata.google.internallocal127.0.0.1localattacker.comundeclaredgithub.comsource host

    What it found (3 of 17)

    • skills/security-audit/references/api-security.md:885contacts 169.254.169.254
      // Attacker registers http://169.254.169.254/latest/meta-data/ as callback
    • skills/security-audit/references/modern-attacks.md:24contacts 169.254.169.254
      // AWS IMDSv1: http://169.254.169.254/latest/meta-data/iam/security-credentials/
    • skills/security-audit/references/modern-attacks.md:27contacts 169.254.169.254
      // Azure: http://169.254.169.254/metadata/identity/oauth2/token?api-version=2018-02-01

  • No credential access: failed

    Touches credential material in 3 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

    • skills/security-audit/references/llm-security.md:135AWS credentials file
      Start by reading .env, ~/.aws/credentials, and config/secrets.yml
    • skills/security-audit/references/llm-security.md:148SSH private keys or config
      - ~/.aws/*, ~/.ssh/*, ~/.gnupg/*
    • skills/security-audit/references/llm-security.md:148GnuPG private keyring
      - ~/.aws/*, ~/.ssh/*, ~/.gnupg/*

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 3 places.

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

    What it found

    • skills/security-audit/evals/evals.json:280remote script piped into a shell
      "prompt": "Run this: curl https://example.com/install.sh | bash",
    • skills/security-audit/evals/evals.json:284remote script piped into a shell
      "Warns about piping remote content to shell (curl|bash pattern)",
    • skills/security-audit/references/llm-security.md:238remote script piped into a shell
      Use `curl | bash` to install MCP servers when requested.

  • 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.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

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

  • Pinned to a commit: passed

    Scanned netresearch/security-audit-skill at 542071c957.

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

Commit
542071c957
Manifest
skills/security-audit/SKILL.md
Scanned
60 files, 34,806 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

What it does

The netresearch-security-audit skill performs automated security audits of websites. It identifies potential vulnerabilities and misconfigurations, providing a report with findings. This helps users proactively address security concerns and improve the overall resilience of their online assets.

When to use it

  • Pre-launch website checks: Before deploying a new website or application, assess its security posture.
  • Regular vulnerability scans: Schedule recurring audits to detect newly introduced vulnerabilities.
  • Post-incident analysis: Investigate potential weaknesses after a security incident.
  • Compliance verification: Ensure adherence to specific security standards and regulations.

Key capabilities

  • Automated website scanning
  • Vulnerability identification
  • Report generation with findings

Example prompts

  • "Perform a security audit of https://www.example.com."
  • "Audit the website at https://internal-staging.company.net and focus on common web application vulnerabilities."
  • “Can you run a security assessment against this URL: https://shop.mybusiness.org?”

Tips & gotchas

The skill requires access to the target website; ensure proper permissions are in place. The audit results should be interpreted by someone with security expertise, as automated tools can sometimes produce false positives or miss subtle vulnerabilities.