Home / Skills / llm-security

llm-security From the maker

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.

Scanned · 1 to knowSkillSource: GitHubFrom the maker (verified org) · no license file

330 stars +3 this week Updated 3mo ago License none (maker) Context ≈152 tokens always loaded

49popular

Why this score

Stars

14/35

Usage (forks)

5/15

Upkeep

15/25

License

5/15

Owner history

10/10

This repo hosts 3 skills, so its 330 stars are split between them (about 110 each) for scoring.

Popularity score: 49/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Oct 20, 2026 at commit 68177b8830f9, with Cisco's open-source skill-scanner.

What its code does:

Runs shell commands Common for dev tools. Read the commands it runs.AGENTS.md:1054, rules/data-poisoning.md:343, rules/excessive-agency.md:35 and 5 more

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

Name	Score	Stars	Context	Updated
This onellm-security semgrep/skills · Skill	49	★ 330	≈152 always	3mo ago
09-web-security Masriyan/Claude-Code-CyberSecurity-Skill · Skill Both about security and owasp	66	★ 490	≈21 always	19d ago
owasp-security agamm/claude-code-owasp · Skill Same job: ai engineering	70	★ 386	≈118 always	1mo ago
analyzing-security telagod/code-abyss · Skill Both about security and owasp	53	★ 244	≈85 always	4mo ago
security-reviewer Mathews-Tom/armory · Subagent Both about security and owasp	62	★ 333	≈23 in chat	17d ago
verify-security Aurite-ai/agent-verifier · Skill Both about security and vulnerability	59	★ 45	≈58 always	22d ago

Install

mkdir -p .claude/skills/llm-security

curl -sL https://codeload.github.com/semgrep/skills/tar.gz/68177b8830f96cd9d10dacbb14dde2566360503d | tar -xz -C .claude/skills/llm-security --strip-components=3 "skills-68177b8830f96cd9d10dacbb14dde2566360503d/skills/llm-security"

To remove it later:

rm -rf .claude/skills/llm-security

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

Pinned to commit 68177b8830f9 as listed by GitHub.

Context cost: ≈152 tokens loaded every session (name and description), plus ≈1.3k tokens when the skill is used.

The Claude Code command downloads this skill folder at the pinned commit into .claude/skills/. The Skills CLI (npx skills) works with many agents but can't pin a version, so it installs whatever is current.

Used for

Engineering › AI engineering Security › Security review Customer support › Support & helpdesk

Facts

Repo: semgrep/skills
Stars: 330
Forks: 32
Last push: 2026-07-28 (3mo ago)
License: No license file (official maker)
Owner: semgrep · since 2017
Language: JavaScript
Works with: Claude Code, Skills CLI