LLM AI Security | Agent Skills Atlas

About this skill

Hunt vulnerabilities in LLM-powered applications — direct/indirect prompt injection, system prompt extraction, ASCII smuggling, RCE via code tools, agentic AI exploits (ASI01-ASI10), data exfiltration via response channels, IDOR in chat history, jailbreak chains, RAG poisoning. Use when target has a chatbot, AI assistant, copilot, or agentic AI features.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

1 potential finding · Scanned 11/4/2026 · Scanner 0.2.1

high: instruction override — SKILL.md, line 31

Content SHA-256: 91de059f0d778801d4ab6840ba233eabc90bf5ae41d186e5f3b664ab5e63a821

About scan coverage and limitations

Original listing metadata

Original name

llm-ai-security

Original description

About this listing

Category: Security
Reported license: MIT
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.