Building Agent Systems
telagod/code-abyss
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…
LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file…
Install LLM Security
$ npx skills add hardw00t/ai-security-arsenal --skill llm-security -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hardw00t/ai-security-arsenal llm-security --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/hardw00t/ai-security-arsenal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/llm-security .claude/skills/llm-security && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "llm-security" agent skill from https://github.com/hardw00t/ai-security-arsenal/tree/main/skills/llm-security into .claude/skills/llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-security", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/hardw00t/ai-security-arsenal/tree/main/skills/llm-securityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add hardw00t/ai-security-arsenal --skill llm-security -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hardw00t/ai-security-arsenal llm-security --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hardw00t/ai-security-arsenal.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/llm-security .agents/skills/llm-security && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "llm-security" agent skill from https://github.com/hardw00t/ai-security-arsenal/tree/main/skills/llm-security into .agents/skills/llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-security", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hardw00t/ai-security-arsenal --skill llm-security -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hardw00t/ai-security-arsenal llm-security --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hardw00t/ai-security-arsenal.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/llm-security .cursor/skills/llm-security && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "llm-security" agent skill from https://github.com/hardw00t/ai-security-arsenal/tree/main/skills/llm-security into .cursor/skills/llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-security", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/hardw00t/ai-security-arsenal.git --path skills/llm-security--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add hardw00t/ai-security-arsenal --skill llm-security -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hardw00t/ai-security-arsenal llm-security --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hardw00t/ai-security-arsenal.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/llm-security .gemini/skills/llm-security && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "llm-security" agent skill from https://github.com/hardw00t/ai-security-arsenal/tree/main/skills/llm-security into .gemini/skills/llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-security", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hardw00t/ai-security-arsenal llm-securityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hardw00t/ai-security-arsenal --skill llm-security -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hardw00t/ai-security-arsenal.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/llm-security .github/skills/llm-security && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "llm-security" agent skill from https://github.com/hardw00t/ai-security-arsenal/tree/main/skills/llm-security into .github/skills/llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-security", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hardw00t/ai-security-arsenal --skill llm-security -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hardw00t/ai-security-arsenal llm-security --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hardw00t/ai-security-arsenal.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/llm-security .opencode/skills/llm-security && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "llm-security" agent skill from https://github.com/hardw00t/ai-security-arsenal/tree/main/skills/llm-security into .opencode/skills/llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-security", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
llm-security- GitHub stars
- 104
- Token cost
- ~2.8k tokens
- SKILL.md length
- 994 words
- Files
- 24 (incl. references)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- None found
At a glance
LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file…
- Requests to test LLM / AI-agent / RAG / MCP / computer-use security
- SKILL.md covers When to Use, When NOT to Use This Skill, Decision Tree and Parallelism Hints, plus 11 more sections
- Calls pip and npm
- Perform prompt injection
What it does
LLM Security is an agent skill from hardw00t/ai-security-arsenal. LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file injection, agentic tool misuse, computer-use UI injection, and excessive agency. Authorization required — this skill tests AI systems you are explicitly permitted to assess. Triggers on requests to test LLM / AI-agent / RAG / MCP / computer-use security, perform prompt injection, extract system prompts, poison RAG or memory…
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 28 other files, including reference files (for example `examples/indirect_injection_doc.md`, `examples/malicious_mcp_response.json` and `examples/poisoned_rag_chunk.md`).
It sits in AI & LLM Engineering, covering Prompt injection and agent security, Prompt engineering and Desktop control. It works with Model Context Protocol. The repository describes itself as: A collection of skills, agents, commands, and workflows for security researchers. Compatible with Claude Code, Claude Desktop, OpenCode, and other AI coding tools.
When your agent uses it
- Requests to test LLM / AI-agent / RAG / MCP / computer-use security
- Perform prompt injection
- Extract system prompts
- Audit agent tool use
Example prompts
- “/llm-security”
Requirements
- Python 3
- Node.js
What it can do on your machine
Read from SKILL.md and the folder at commit a1a68f7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pipnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip and npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
LLM Security loads about 2.8k tokens when it runs, and up to ~8.8k if it reads all its reference files. Until then it costs about 145 tokens; SKILL.md has 994 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 994 words (~2,754 tokens).
“Thin router skill for security testing of LLM applications and AI agents. Covers the OWASP LLM Top 10 (2025) with a 2026-grade threat model for frontier-model agentic systems: indirect injection, multimodal injection, MCP supply chain, memory poisoning, skill-file injection, computer-use…”
- name
- llm-security
Files
SKILL.md and 23 other files (references) in skills/llm-security of hardw00t/ai-security-arsenal.
- SKILL.md
- examples/indirect_injection_doc.md
- examples/malicious_mcp_response.json
- examples/poisoned_rag_chunk.md
- payloads/encoding_obfuscation.txt
- payloads/injection_2026.txt
- payloads/legacy_jailbreaks.txt
- payloads/multimodal_injection.md
- payloads/system_prompt_extraction.txt
- references/bounty_patterns_2024_2026.md
- references/defense_patterns_2026.md
- references/owasp_llm_top10_2025.md
- references/threat_model_agents.md
- schemas/finding.json
- workflows/agentic_tool_misuse.md
- workflows/computer_use_abuse.md
- … and 8 more
Open the folder on GitHubat commit a1a68f7
Compare with similar skills
LLM Security next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| LLM Security this skillhardw00t/ai-security-arsenal | 104 | — | ~2.8k | Automated safety check: Pass | None | |
| Building Agent Systemstelagod/code-abyss | 243 | — | ~691 | Automated safety check: Pass | MIT | |
| AI Learning JournalLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.6k | Automated safety check: Pass | MIT | |
| AI LLM Agent Securityzhaji2333/CkSKILLS | 113 | — | ~4.7k | Automated safety check: Warn | MIT | |
| Hunt LLM AIelementalsouls/Claude-BugHunter | 4.8k | — | ~4k | Automated safety check: Warn | MIT | |
| Moai Ref LLM Securitymodu-ai/moai-adk | 1.2k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
AI Learning Journal
LeoYeAI/openclaw-master-skills
AI 学习记录与成长追踪工具。用于记录 AI/LLM 学习笔记、使用心得、Prompt 技巧、工具体验等，并提供学习指导和规划。当用户提到以下任何话题时都应使用此 skill：AI 学习记录、学习笔记、AI 使用心得、Prompt 工程学习、模型对比体验、AI 工具使用记录、LLM 学习、RAG 学习、Agent 学习、MCP 学习、AI 微调实践、AI 学习规划、怎么学 AI、AI…
AI LLM Agent Security
zhaji2333/CkSKILLS
当目标为 LLM 应用/Chatbot/智能客服/AI 助手/Copilot/Agent/RAG 知识库/多模态模型，或发现用户输入进入大模型提示、工具调用、知识库检索、对话记忆、文件解析，或需要测试提示词注入/越狱逃逸/System Prompt 泄露/训练数据与敏感信息泄露/RAG 检索污染/Agent 记忆污染/工具滥用与命令执行/SSRF/沙箱逃逸时调用。负责 OWASP LLM…
Hunt LLM AI
elementalsouls/Claude-BugHunter
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10).
Moai Ref LLM Security
modu-ai/moai-adk
AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning detection, model-output validation and…
Agent Harness Design
AnastasiyaW/codex-claude-code-config
Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool results, agent budgets (10 types), context trust labels against…
More from hardw00t/ai-security-arsenal
Dast Automation
hardw00t/ai-security-arsenal
Automated Dynamic Application Security Testing (DAST) using Playwright MCP plus standard OS pentest tooling.
Sast Orchestration
hardw00t/ai-security-arsenal
Static Application Security Testing orchestration — run and compose Semgrep, CodeQL, Bandit, gosec, Brakeman, SpotBugs, ESLint; author custom rules; ingest SARIF; triage and rank findings by…
Container Security
hardw00t/ai-security-arsenal
Container and Kubernetes security assessment — image vulnerability scanning, SBOM diff analysis, K8s cluster auditing, RBAC privilege mapping, NetworkPolicy review, container escape testing, and…
Iac Security
hardw00t/ai-security-arsenal
Infrastructure-as-Code security scanning router for Terraform, CloudFormation, Kubernetes manifests, Helm, ARM/Bicep.
Sca Security
hardw00t/ai-security-arsenal
Software Composition Analysis: find vulnerable dependencies, correlate CVE/GHSA/OSV across ecosystems, generate CycloneDX/SPDX SBOMs, assess license compliance, and run reachability-aware triage to…
Threat Modeling
hardw00t/ai-security-arsenal
Systematic threat modeling skill for applications, APIs, and systems using STRIDE, PASTA, Attack Trees, DREAD, LINDDUN, and OCTAVE.
Related
Works with
Categories
Questions about LLM Security
What does LLM Security do?
LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file…. LLM Security is an agent skill from hardw00t/ai-security-arsenal. LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file injection, agentic tool misuse, computer-use UI injection, and excessive agency.
When should I use LLM Security?
LLM Security fits situations like: requests to test LLM / AI-agent / RAG / MCP / computer-use security; perform prompt injection; extract system prompts; audit agent tool use.
How do I install LLM Security in Claude Code?
Run `npx skills add hardw00t/ai-security-arsenal --skill llm-security -a claude-code`. Or copy the skill folder (skills/llm-security in hardw00t/ai-security-arsenal) into .claude/skills/llm-security in your project. Claude Code loads it when a task matches its description.
How do I install LLM Security in Codex?
Run `npx skills add hardw00t/ai-security-arsenal --skill llm-security -a codex`. Or copy the skill folder (skills/llm-security in hardw00t/ai-security-arsenal) into .agents/skills/llm-security in your project. Codex loads it when a task matches its description.
Can I use LLM Security in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hardw00t/ai-security-arsenal --skill llm-security -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/llm-security, .gemini/skills/llm-security, .github/skills/llm-security and .opencode/skills/llm-security in your project.
What does LLM Security need to run?
Going by SKILL.md and its folder, LLM Security needs the command-line tools its instructions call (pip and npm). Our summary lists: Python 3; Node.js.
Does LLM Security access the network?
SKILL.md contains no URLs. Its commands use pip and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is LLM Security safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does LLM Security use?
No licence was found for LLM Security or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does LLM Security use?
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6k tokens, read only when the agent opens those files.
What are the alternatives to LLM Security?
Skills that share tags, products or a category with LLM Security: Building Agent Systems (telagod/code-abyss, 243 stars), AI Learning Journal (LeoYeAI/openclaw-master-skills, 2.2k stars), AI LLM Agent Security (zhaji2333/CkSKILLS, 113 stars) and Hunt LLM AI (elementalsouls/Claude-BugHunter, 4.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains LLM Security?
hardw00t (a GitHub user) maintains it in hardw00t/ai-security-arsenal, which has 104 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on April 19, 2026.
Source: hardw00t/ai-security-arsenal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.