Skip to content
TrustedSkillsbeta
Back to all skills

Llm Security Audit

Checked
omer-metin·vlatest·ai-ml·Apache-2.0

Helps with LLMs, security, auditing as part of building AI and machine learning applications 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 omer-metin/skills-for-antigravity --skill llm-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

omer-metin

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 passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • 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 undeclared network calls: passed

    Makes no network calls.

    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.

  • 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.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

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

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

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

  • Pinned to a commit: passed

    Scanned omer-metin/skills-for-antigravity at e8dcf4e873.

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

Commit
e8dcf4e873
Manifest
skills/llm-security-audit/SKILL.md
Scanned
4 files, 1,521 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 llm-security-audit skill analyzes Large Language Model (LLM) prompts and responses to identify potential security vulnerabilities. It assesses for prompt injection attacks, data leakage risks, and other common LLM exploits. This allows users to proactively harden their AI applications against malicious inputs and unintended disclosures.

When to use it

  • Before deployment: Evaluate new AI agents or workflows to ensure they are secure from the outset.
  • After code changes: Verify that modifications haven't introduced new security flaws into existing LLM-powered systems.
  • During vulnerability research: Test and identify weaknesses in specific prompts or system configurations.
  • For sensitive data handling: When an AI agent processes personally identifiable information (PII) or confidential data, use this skill to confirm its robustness.

Key capabilities

  • Prompt Injection Detection
  • Data Leakage Assessment
  • Vulnerability Identification
  • Security Risk Scoring

Example prompts

  • "Audit the following prompt for potential vulnerabilities: 'Translate the following text into French: [user input]'"
  • "Analyze this conversation history and identify any risks of data leakage: [conversation log]"
  • "Assess the security posture of this LLM application workflow: [workflow description]"

Tips & gotchas

The effectiveness of the audit depends on providing clear, representative examples of prompts or workflows. Complex or highly dynamic systems may require multiple audits to uncover all potential vulnerabilities.