LLM Security
sickn33/agentic-awesome-skills
Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and agent-compliance engineering per OWASP…
OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction.
Install Common LLM Security
$ npx skills add HoangNguyen0403/agent-skills-standard --skill common-llm-security -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HoangNguyen0403/agent-skills-standard common-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/HoangNguyen0403/agent-skills-standard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/common/common-llm-security .claude/skills/common-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 "common-llm-security" agent skill from https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/skills/common/common-llm-security into .claude/skills/common-llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "common-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/HoangNguyen0403/agent-skills-standard/tree/develop/skills/common/common-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 HoangNguyen0403/agent-skills-standard --skill common-llm-security -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HoangNguyen0403/agent-skills-standard common-llm-security --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/common/common-llm-security .agents/skills/common-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 "common-llm-security" agent skill from https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/skills/common/common-llm-security into .agents/skills/common-llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "common-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 HoangNguyen0403/agent-skills-standard --skill common-llm-security -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HoangNguyen0403/agent-skills-standard common-llm-security --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/common/common-llm-security .cursor/skills/common-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 "common-llm-security" agent skill from https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/skills/common/common-llm-security into .cursor/skills/common-llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "common-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/HoangNguyen0403/agent-skills-standard.git --path skills/common/common-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 HoangNguyen0403/agent-skills-standard --skill common-llm-security -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HoangNguyen0403/agent-skills-standard common-llm-security --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/common/common-llm-security .gemini/skills/common-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 "common-llm-security" agent skill from https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/skills/common/common-llm-security into .gemini/skills/common-llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "common-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 HoangNguyen0403/agent-skills-standard common-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 HoangNguyen0403/agent-skills-standard --skill common-llm-security -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/common/common-llm-security .github/skills/common-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 "common-llm-security" agent skill from https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/skills/common/common-llm-security into .github/skills/common-llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "common-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 HoangNguyen0403/agent-skills-standard --skill common-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 HoangNguyen0403/agent-skills-standard common-llm-security --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/common/common-llm-security .opencode/skills/common-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 "common-llm-security" agent skill from https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/skills/common/common-llm-security into .opencode/skills/common-llm-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "common-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
common-llm-security- GitHub stars
- 572
- Token cost
- ~921 tokens
- SKILL.md length
- 389 words
- Files
- 3 (incl. references)
- Skills in repo
- 211
- Repo updated
- First seen
- Licence
- MIT
At a glance
OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction.
- Performing any security review touching LLM client code
- SKILL.md covers Priority: P0 (CRITICAL), Implementation Guidelines, OWASP LLM Top 10 (2025) and Anti-Patterns, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Prompt templates
What it does
Common LLM Security is an agent skill from HoangNguyen0403/agent-skills-standard. OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction. Use when performing any security review touching LLM client code, prompt templates, agent tools, or vector stores.
Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `evals/evals.json` and `references/owasp-llm.md`).
It sits in Security, covering Web application vulnerabilities, Prompt injection and agent security and Security review. The repository describes itself as: A collection of Agent Skills Standard and Best Practice for Programming Languages, Frameworks that help our AI Agent follow best practies on frameworks and programming laguages. The licence is MIT.
When your agent uses it
- Performing any security review touching LLM client code
- Prompt templates
Example prompts
- “/common-llm-security”
What it can do on your machine
Read from SKILL.md and the folder at commit b529c2d. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Common LLM Security loads about 921 tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 389 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
The full file from HoangNguyen0403/agent-skills-standard at commit b529c2d, republished under its MIT licence (© HoangNguyen0403). 389 words, ~921 tokens.
Download SKILL.mdSave it as
.claude/skills/common-llm-security/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- common-llm-security
- description
- OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction. Use when performing any security review touching LLM client code, prompt templates, agent tools, or vector stores.
- guardrail
- true
OWASP LLM Top 10 Security Checklist (2025)
Priority: P0 (CRITICAL)
Implementation Guidelines
- Check LLM01 first: Prompt injection #1 LLM finding — any user input concatenated directly into prompt string immediate P0.
- Check LLM06 next: Agent tools with write/delete/execute capabilities without confirmation P0.
- Mark each item: ✅ not affected | ⚠️ needs review | 🔴 confirmed finding.
- P0 finding caps Security score at 40/100 — not skip any item.
- See references/owasp-llm.md for full detection signals.
- Agent skill supply chain: Review all package resources; pin source revision and hashes. Treat hashes as integrity, not trusted authorship.
- Memory poisoning: Treat logs, retrieved documents and proposed learning entries as untrusted data; redact before persistence.
- Permission boundaries: Tool/network/filesystem restrictions require host enforcement; skill text and
allowed-toolsdeclarations are not universal enforcement. - Evolution approval: Separate candidate author from approval; block promotion without independent review and verified evidence.
- Offline fallback: Unsupported execution controls block live actions, not safe offline analysis of supplied artifacts.
OWASP LLM Top 10 (2025)
| ID | Risk | Key Detection Signal |
|---|---|---|
| LLM01 | Prompt Injection | User input string-concatenated into prompt. Retrieved docs inserted into system turn. |
| LLM02 | Sensitive Information Disclosure | PII or credentials passed into prompt context. LLM response logged without redaction. |
| LLM03 | Supply Chain | Unverified model weights or plugins. Third-party agent added without trust review. |
| LLM04 | Data & Model Poisoning | User-controlled data written to training sets or embedding stores without validation. |
| LLM05 | Improper Output Handling | LLM output used directly in DOM sink, SQL query, shell command, or redirect URL. |
| LLM06 | Excessive Agency | Agent tool with write/delete/network access — no human-in--loop confirmation. |
| LLM07 | System Prompt Leakage | System prompt content returned via tool output, error message, or API response. |
| LLM08 | Vector & Embedding Weaknesses | User text injected into vector store without sanitization. No tenant namespace isolation. |
| LLM09 | Misinformation | LLM output used for critical decisions (medical, financial, legal) without verification. |
| LLM10 | Unbounded Consumption | No max_tokens on LLM call. No rate limit on invocations. Agent loop without depth cap. |
Show full SKILL.md (79 more words)Show less
Anti-Patterns
- No prompt concat: Pass user input as separate
userturn, never interpolated into system prompts. - No raw LLM output in sinks: Sanitize LLM responses before writing to DOM, queries, or shell.
- No uncapped agent loops: Every agentic recursion must enforce max iteration/depth limit.
References
- OWASP LLM — Full Detection Signals — load when auditing any LLM client code
Canonical response anchors
When this skill applies, preserve the following domain terminology or equivalent concrete examples in the answer when relevant:
- sanitize
© HoangNguyen0403, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/common/common-llm-security of HoangNguyen0403/agent-skills-standard.
- SKILL.md
- evals/evals.json
- references/owasp-llm.md
Open the folder on GitHubat commit b529c2d
Compare with similar skills
Common 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 |
|---|---|---|---|---|---|---|
| Common LLM Security this skillHoangNguyen0403/agent-skills-standard | 572 | — | ~921 | Automated safety check: Pass | MIT | |
| LLM Securitysickn33/agentic-awesome-skills | 47k | 1 repos | ~1.2k | Automated safety check: Warn | MIT | |
| Secureclawadversa-ai/secureclaw | 347 | 1 repos | ~193 | Automated safety check: Pass | MIT | |
| Csono-session/pstack | 136 | — | ~12k | Automated safety check: Notes | MIT | |
| AI LLM Agent Securityzhaji2333/CkSKILLS | 115 | — | ~4.7k | Automated safety check: Warn | MIT | |
| MCP Server Security Auditawarexone/Agentic-Bug-Hunter | 5.3k | — | ~1.9k | Automated safety check: Warn | MIT |
Similar skills
Secureclaw
adversa-ai/secureclaw
Security hardening toolkit for OpenClaw. An agent skill from adversa-ai/secureclaw.
Cso
no-session/pstack
Chief Security Officer mode. An agent skill from no-session/pstack.
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…
MCP Server Security Audit
awarexone/Agentic-Bug-Hunter
Audits MCP servers and their client configs for tool poisoning, prompt injection, over-privileged tools, injection bugs, secret leaks and missing approval gates.
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).
More from HoangNguyen0403/agent-skills-standard
All 211 skills in this repoSubagent-Driven Development
HoangNguyen0403/agent-skills-standard
Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.
draw.io Architecture Diagramming
HoangNguyen0403/agent-skills-standard
Draws architecture diagrams as editable draw.io files from a JSON spec, with a fixed house style, one C4 level per diagram and evidence-tagged shapes.
Android Navigation 3 Guide
HoangNguyen0403/agent-skills-standard
Implements and migrates to Jetpack Navigation 3 in Compose: NavDisplay, typed route objects, a state-list back stack, deep links, multiple back stacks and dialog scenes.
Angular HttpClient Standards
HoangNguyen0403/agent-skills-standard
Sets rules for Angular HTTP code: functional interceptors, typed requests, services that own every call, and httpResource for reactive data loading in Angular 17+.
Angular Tooling
HoangNguyen0403/agent-skills-standard
Angular CLI usage, code generation, build configuration, and bundle optimization.
Common Code Review
HoangNguyen0403/agent-skills-standard
Conduct high-quality, persona-driven code reviews. An agent skill from HoangNguyen0403/agent-skills-standard.
Related
Categories
Questions about Common LLM Security
What does Common LLM Security do?
OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction. Common LLM Security is an agent skill from HoangNguyen0403/agent-skills-standard. OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction.
When should I use Common LLM Security?
Common LLM Security fits situations like: performing any security review touching LLM client code; prompt templates.
How do I install Common LLM Security in Claude Code?
Run `npx skills add HoangNguyen0403/agent-skills-standard --skill common-llm-security -a claude-code`. Or copy the skill folder (skills/common/common-llm-security in HoangNguyen0403/agent-skills-standard) into .claude/skills/common-llm-security in your project. Claude Code loads it when a task matches its description.
How do I install Common LLM Security in Codex?
Run `npx skills add HoangNguyen0403/agent-skills-standard --skill common-llm-security -a codex`. Or copy the skill folder (skills/common/common-llm-security in HoangNguyen0403/agent-skills-standard) into .agents/skills/common-llm-security in your project. Codex loads it when a task matches its description.
Can I use Common 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 HoangNguyen0403/agent-skills-standard --skill common-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/common-llm-security, .gemini/skills/common-llm-security, .github/skills/common-llm-security and .opencode/skills/common-llm-security in your project.
What does Common LLM Security need to run?
SKILL.md names no scripts, command-line tools or credentials: Common LLM Security is instructions for the agent only.
Does Common LLM Security access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Common 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 Common LLM Security use?
Common LLM Security is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Common LLM Security use?
About 921 tokens (SKILL.md is roughly 3.7k 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 1.4k tokens, read only when the agent opens those files.
What are the alternatives to Common LLM Security?
Skills that share tags, products or a category with Common LLM Security: LLM Security (sickn33/agentic-awesome-skills, 47k stars), Secureclaw (adversa-ai/secureclaw, 347 stars), Cso (no-session/pstack, 136 stars) and AI LLM Agent Security (zhaji2333/CkSKILLS, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Common LLM Security?
HoangNguyen0403 (a GitHub user) maintains it in HoangNguyen0403/agent-skills-standard, which has 572 GitHub stars. The repository holds 211 skills in this directory. The repository was last updated on October 9, 2026.
Source: HoangNguyen0403/agent-skills-standard on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.