Defend LLM Top 10
Defensive playbook for the OWASP Top 10 for LLM Applications (2025), centered on prompt injection (MITRE ATLAS AML.T0051, direct and indirect), RAG retrieval abuse (LLM08), and improper output handling (LLM05). Prompt injection has no patch, so defense is logging, blast-radius design, and breaking the lethal-trifecta exfiltration path, as seen in EchoLeak (CVE-2025-32711). Keys off LLM app telemetry: prompt and completion logs, tool-call audit events, RAG retrieval logs, guardrail verdicts, the Purview unified audit log for Copilot, and Azure OpenAI diagnostics. Ships a canary-token tripwire, an egress/exfiltration detection, a tool-call fan-out rule, required logging, and a mitigation table. Use when threat-modeling an LLM, RAG, or agent feature, deciding what to log, writing detections for prompt injection or system-prompt leakage, hunting copilot data exfiltration, or triaging an EchoLeak-style incident.
Security AStatic scan found no risk patternsHow grading works ›
From the source SKILL.md
Your organization is shipping LLM features whether security signed off or not: chatbots, copilots, RAG over internal documents, agents with tool access. This skill reads the OWASP Top 10 for LLM Applications (2025) as a defender's checklist and ships the detections that work today. It is defensive: it describes injection classes only to the depth needed to log, detect, and contain them, and provides no working injection payloads, jailbreak strings, or evasion techniques.
What this skill does
Defend LLM Top 10 is a community-contributed Claude Code skill in the web-security sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/defend-llm-top-10/ and loads when your prompt matches the skill's trigger.
When to invoke it: Use when threat-modeling an LLM, RAG, or agent feature, deciding what to log, writing detections for prompt injection or system-prompt leakage, hunting copilot data exfiltration, or triaging an EchoLeak-style incident.
Who uses this skill
The Defend LLM Top 10 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 211,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
How to install
Free
Manual install (2 steps)
mkdir -p ~/.claude/skills/defend-llm-top-10
curl -L https://claudskills.com/skills/defend-llm-top-10/SKILL.md \
-o ~/.claude/skills/defend-llm-top-10/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/defend-llm-top-10/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/defend-llm-top-10/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\defend-llm-top-10\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Telegram
📱 Install from your phone or desktop Telegram
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 →
Pro
One-click install via the desktop app
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.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
Frequently asked questions
How do I install the Defend LLM Top 10 Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy
SKILL.md from the source repository to
~/.claude/skills/defend-llm-top-10/SKILL.md and restart Claude Code. Both flows are detailed at
claudskills.com/install/.
What does the Defend LLM Top 10 skill do?
Defensive playbook for the OWASP Top 10 for LLM Applications (2025), centered on prompt injection (MITRE ATLAS AML.T0051, direct and indirect), RAG retrieval abuse (LLM08), and improper output handling (LLM05). Prompt injection has no patch, so defense is logging, blast-radius design, and breaking the lethal-trifecta exfiltration path, as seen in EchoLeak (CVE-2025-32711). Keys off LLM app telemetry: prompt and completion logs, tool-call audit events, RAG retrieval logs, guardrail verdicts, the Purview unified audit log for Copilot, and Azure OpenAI diagnostics. Ships a canary-token tripwire, an egress/exfiltration detection, a tool-call fan-out rule, required logging, and a mitigation table. Use when threat-modeling an LLM, RAG, or agent feature, deciding what to log, writing detections for prompt injection or system-prompt leakage, hunting copilot data exfiltration, or triaging an EchoLeak-style incident.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Defend LLM Top 10 skill?
Use Defend LLM Top 10 when your Claude Code task falls under the Security category — specifically in the web security area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Defend LLM Top 10" or describe the task and let Claude pick). Browse related skills at
/category/security/.
What is a Claude Code skill and how does the Defend LLM Top 10 skill fit in?
A Claude Code skill is a
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. Defend LLM Top 10 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/.
Attribution & license
Cite this skill
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
APA
umbrasec-labs. (2026). Defend LLM Top 10 [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/defend-llm-top-10/
BibTeX
@misc{defend-llm-top-10-2026,
author = {umbrasec-labs},
title = {Defend LLM Top 10 [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/defend-llm-top-10/}
}Embed this skill
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Badge
[](https://claudskills.com/skills/defend-llm-top-10/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/defend-llm-top-10.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/defend-llm-top-10.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Defend LLM Top 10"></iframe>
Security scan
Grade A · scanned 2026-10-25 — free static scan against the OWASP Agentic Skills Top 10.
No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›
- ✓ Prompt injection
- ✓ Data exfiltration
- ✓ Supply chain
- ✓ Reverse shell
- ✓ Credentials
- ✓ Execution
- ✓ Filesystem
- ✓ Persistence
- ✓ Obfuscation
- ✓ Network
Show this grade on your repo (click to copy):
[](https://claudskills.com/skills/defend-llm-top-10/#security)
More Security skills
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