llm-security — Claude Code skill: LLM security and setup
This skill checks LLM applications against OWASP Top 10 for LLM 2025. Use it for chatbots, RAG pipelines, agents, and LLM APIs.
npx skills add semgrep/skills --skill llm-security -a claude-codeWhat llm-security does
llm-security gives an LLM application review a security checklist tied to its architecture. It works proactively while building or reviewing a system, and reactively when someone asks about a vulnerability. The workflow maps chatbots, RAG, tool-using agents, training, APIs, and content generation to their main risks.
The package includes a workflow plus rules/ files with vulnerable and safer code examples. The rule set covers prompt injection, sensitive disclosure, supply chain issues, data poisoning, output handling, excessive agency, prompt leakage, vector weaknesses, misinformation, and unbounded consumption. Detailed guidance depends on reading the relevant files in rules/, not just the priority map.
What it helps with
- check a chatbot for prompt injection
- review a RAG pipeline for data exposure
- limit permissions granted to an LLM agent
- sanitize model output before downstream use
- spot unbounded LLM resource consumption
Example prompts for the agent
- Review this chatbot against OWASP Top 10 for LLM 2025 and flag the highest-priority risks.
- Audit this RAG pipeline for prompt injection, sensitive disclosure, and vector or embedding weaknesses.
- Check this tool-using LLM agent for excessive agency and unsafe output handling.
How to install llm-security
1Skills CLI (Vercel)
npx skills add semgrep/skills --skill llm-security -a claude-code2Manually: put the files in place
~/.claude/skills/llm-security/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/llm-security/
1Skills CLI (Vercel)
npx skills add semgrep/skills --skill llm-security -a codex2Manually: put the files in place
.agents/skills/llm-security/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add semgrep/skills --skill llm-security -a cursor2Manually: put the files in place
.cursor/skills/llm-security/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install semgrep/skills llm-security2Manually: put the files in place
.github/skills/llm-security/SKILL.md1Skills CLI (Vercel)
npx skills add semgrep/skills --skill llm-security -a gemini-cli2Platform CLI
gemini skills install https://github.com/semgrep/skills --path skills/llm-securityManually: put the files in place
.devin/skills/llm-security/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add semgrep/skills --skill llm-security -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about llm-security
How do I install llm-security in Claude Code?
Run npx skills add semgrep/skills --skill llm-security -a claude-code, then use ~/.claude/skills/llm-security/SKILL.md.
What does llm-security do?
It guides security reviews of LLM applications using OWASP Top 10 for LLM 2025 and selects relevant checks for systems such as chatbots, RAG pipelines, agents, and APIs.
Which RAG risks does it prioritize?
For RAG systems, it prioritizes vector and embedding weaknesses, prompt injection, sensitive information disclosure, and misinformation.
