Skip to content
TrustedSkillsbeta
Back to all skills

Owasp Llm Top10

Checked
mastepanoski·vlatest·ai-ml·MIT

Provides LLMs guidance and assistance for building AI and machine learning applications.

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 mastepanoski/claude-skills --skill owasp-llm-top10 -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

mastepanoski

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 mastepanoski/claude-skills at fbdde8adb5.

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

Commit
fbdde8adb5
Manifest
skills/owasp-llm-top10/SKILL.md
Scanned
1 file, 704 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 helps mitigate risks associated with Large Language Model (LLM) applications, based on the OWASP Top 10 LLM Security Risks. It provides guidance and checks to address vulnerabilities like prompt injection, data leakage, denial of service, and insecure output handling. The skill aims to improve the security posture of AI agents interacting with LLMs by identifying and addressing potential weaknesses.

When to use it

  • Developing a new AI agent: Integrate this skill early in development to proactively identify and address security risks.
  • Reviewing existing AI agent prompts: Use it to assess current prompts for vulnerabilities outlined in the OWASP Top 10.
  • Troubleshooting unexpected LLM behavior: When an LLM exhibits unusual or potentially harmful responses, leverage this skill to investigate underlying security issues.
  • Ensuring compliance with security best practices: Implement this skill as part of a broader effort to adhere to industry-standard LLM security guidelines.

Key capabilities

  • OWASP Top 10 LLM Risk Coverage: Addresses the ten most critical risks identified by OWASP for LLM applications.
  • Prompt Analysis: Examines prompts for potential vulnerabilities like prompt injection and insecure data handling.
  • Output Validation: Checks generated output for harmful content or sensitive information leakage.

Example prompts

  • "Analyze this prompt for security vulnerabilities: 'Write a poem about cats.'"
  • "Review the following conversation log for any signs of prompt injection attacks."
  • "Assess this AI agent's response to user input for potential data leakage."

Tips & gotchas

The OWASP Top 10 LLM risks are constantly evolving. Regularly update and re-evaluate your prompts and configurations using this skill to remain protected against emerging threats.