Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HoangNguyen0403/agent-skills-standard --skill common-llm-securitygit clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/common-llm-security)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/common-llm-security"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/common-llm-security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/common-llm-security"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/common-llm-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 24 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 41 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.00705 |
| Opus 5 | $0.00028 | $0.00352 |
| Sonnet 5 | $0.00011 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
common-llm-security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
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. |
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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 58 lines · 56 tokens per session scan A eea5bf8560c3
common-llm-security is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 705 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
elite-engineer
The operating system for elite software engineering in TypeScript, React, and Next.js. Enforces the cognitive models, architecture laws, type-level patterns, component design, visual standards, and performance mandates that separate exceptional software from the ordinary — grounded in named sources (Torvalds…
oma-frontend
Frontend specialist for React, Next.js, Angular, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, shadcn, Angular, and RxJS work.
design-patterns
Frontend design patterns with React 19.2 and TypeScript 6 examples (Composition, Compound Components, Custom Hooks, Render Props, HOC, State Machines). Use when user asks "implement pattern", "use composition", or when designing reusable components.
react-nextjs
React 19.2 + Next.js 16 development - Server Components, Cache Components, proxy.ts, View Transitions, App Router, TypeScript 6, and Tailwind CSS v4. Use when building frontend apps, creating components, or asking "how do I set up X?".
code-quality
Comprehensive frontend code review for TypeScript 6 and React 19.2 — clean code principles, component patterns, type safety, accessibility, and performance. Use when user says "review code", "refactor", "check this PR", or before merging changes.
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.