Web-app security (OWASP, auth, input validation) does not cover the threats that matter most for autonomous LLM agents: prompt injection, capability escalation through memory, and blast-radius accumulation. This skill is the structural playbook for those threats.
LLM Agent Security Principles is a community-contributed Claude Code skill in the zero-trust sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/llm-agent-security-principles/ and loads when your prompt matches the skill's trigger.
When to invoke it: Use when designing a new agent, reviewing agent architecture, adding a new capability, or auditing an existing agent for prompt injection resistance. Covers three load-bearing principles — Security by Absence, Untrusted Content Boundary, One External Adapter — plus concrete defense patterns for HTTP, credentials, and LLM hosts.
The LLM Agent Security Principles Claude Code skill is built for security engineers, penetration testers, DevSecOps practitioners, and development teams hardening codebases and infrastructure. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 163,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
mkdir -p ~/.claude/skills/llm-agent-security-principles curl -L https://claudskills.com/skills/llm-agent-security-principles/SKILL.md \ -o ~/.claude/skills/llm-agent-security-principles/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/llm-agent-security-principles/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/llm-agent-security-principles/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\llm-agent-security-principles\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
SKILL.md from the source repository to ~/.claude/skills/llm-agent-security-principles/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. LLM Agent Security Principles is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Security category. Learn more at /learn/what-is-a-claude-skill/.If you reference this skill in a blog post, paper, or documentation, you can cite it as:
@misc{llm-agent-security-principles-2026,
author = {shimo4228},
title = {LLM Agent Security Principles [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/llm-agent-security-principles/}
}Grade A · scanned 2026-07-28 — free static scan against the OWASP Agentic Skills Top 10.
The scan flagged 1 of 10 categories (execution), including lower-severity patterns. Patterns shown inside code fences are weighted as examples rather than instructions — read the grading methodology for what this does and does not guarantee.
Browse all Security skills in the ClaudSkills registry, or explore these other picks from the same category:
Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel · Telegram @acreatorstore
SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.