Agent Native

llm-security

This skill provides security guidelines for LLM applications based on the OWASP Top 10 for LLM 2025.

by SemgrepOfficial publisher

Identity proven by GitHub's verified organisation badge (semgrep)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License
LicenseRef-Semgrep-Rules (restricted)
Pin
68177b8pinned Oct 9, 2026
Context cost
about 1,100 tokenswhen the skill loads
GitHub stars
322on semgrep/skills
Scripts
None found

What it does

“Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots, AI agents, RAG pipelines, tool-using LLMs, agentic systems, or any application that calls an LLM API (OpenAI, Anthropic, Gemini, etc.) — even if the user doesn't explicitly mention security. Also use when users import 'openai', 'anthropic', 'langchain', 'llamaindex', or similar LLM libraries.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill provides security guidelines for LLM applications based on the OWASP Top 10 for LLM 2025. It helps agents identify and mitigate ten categories of vulnerabilities including prompt injection, sensitive data disclosure, supply chain risks, and output handling issues. The skill includes detailed rule files with code examples for building secure chatbots, RAG systems, AI agents with tools, and other LLM-powered applications.

When to use it

  • Building or reviewing any application that calls an LLM API or imports LLM libraries
  • Developing chatbots, RAG systems, AI agents with tools, or content generation systems
  • Assessing LLM security risks or addressing specific vulnerabilities like prompt injection
  • Implementing access controls and output sanitization in LLM applications

When not to

  • For general software security unrelated to LLMs or AI systems
  • When security review is delegated entirely to specialized security teams without agent involvement
  • If the application does not involve LLM APIs or language model calls

Install

Restricted license: install from the publisher's repository and read its terms.

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add semgrep/skills --skill llm-security

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install semgrep/skills llm-security@68177b8830f96cd9d10dacbb14dde2566360503d

Installs the commit we checked (68177b8).

Copy by hand

Download the folder at 68177b8 and put it in .claude/skills/llm-security for Claude Code and in .agents/skills/llm-security for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 68177b8

Claude Code plugin

/plugin install semgrep@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "llm-security" by Semgrep.

Source, pinned to commit 68177b8830f96cd9d10dacbb14dde2566360503d:
https://github.com/semgrep/skills/tree/68177b8830f96cd9d10dacbb14dde2566360503d/skills/llm-security

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/llm-security/ for Claude Code and .agents/skills/llm-security/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Its license is restricted or not stated. Show me the license terms from the repository before you copy anything.

Listing and checks: https://www.agentnative.dev/skills/semgrep/llm-security

SKILL.md at the pin

The license of this skill does not let us show its files here.

View SKILL.md on GitHub at 68177b8

Files

14 files, 226 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 68177b8
All 6 skills from Semgrep

More from Semgrep

  • code-security

    This skill provides comprehensive security guidelines for writing secure code across 15+ languages, covering OWASP Top 10 vulnerabilities and infrastructure…

    Claude Code, Codex, Cursor +4 · about 1.1K tokens · pinned 7 days ago

  • semgrep

    This skill enables the agent to run Semgrep static analysis scans for security vulnerabilities and create custom detection rules in YAML.

    Claude Code, Codex, Cursor +4 · about 2.2K tokens · pinned 7 days ago

  • add-and-validate-guardian-developer-semgrep-rule

    This skill helps developers write custom Semgrep rules and add them to Guardian to enforce project conventions or catch patterns Guardian's standard rules miss.

    Claude Code · about 2.1K tokens · pinned 7 days ago

  • remove-guardian-developer-semgrep-rule

    This skill removes custom Semgrep rules that Guardian maintains in user or repository directories.

    Claude Code · about 940 tokens · pinned 7 days ago

  • setup-semgrep-plugin

    This skill installs and configures Semgrep on the agent's system, including authentication with Semgrep's service and verification that version 1.146.0 or…

    Claude Code, Codex, Cursor +4 · about 190 tokens · pinned 7 days ago

All Security skills

Related in Security

  • claude-security

    Scans your repository for security issues using Claude, examines code changes or commits for vulnerabilities, and generates patch files to fix findings.

    by AnthropicOfficial publisher

    Claude Code · about 1K tokens · pinned 7 days ago

  • sensitive-logging-audit

    The skill helps audit and fix sensitive data leaks in Python SDK logging, exceptions, and telemetry by collecting candidate sinks, manually tracing values…

    by OpenAIOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 970 tokens · pinned 7 days ago

  • security-audit

    This skill guides security audits of codebases, APIs, and services by finding vulnerabilities that cross real trust boundaries.

    by CloudflareOfficial publisher

    Contains scripts

    Claude Code · about 5.4K tokens · pinned 7 days ago

  • assess-patch-risk

    This skill analyzes patch artifacts to assess their program impact, regression risk, and suitability for automated merging.

    by OpenAIOfficial publisher

    Codex · about 2.3K tokens · pinned 7 days ago

  • attack-path-analysis

    This skill analyzes security findings to build explicit attack paths from source to sink, calibrates severity, and decides whether each finding is reportable.

    by OpenAIOfficial publisher

    Codex · about 2.1K tokens · pinned 7 days ago

  • deep-security-scan

    Performs exhaustive, multi-pass security analysis across a repository or scoped directory by running repeated independent security scans and aggregating…

    by OpenAIOfficial publisher

    Codex · about 3.4K tokens · pinned 7 days ago

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use