Home / hoangnguyen0403 / agent-skills-standard · .claude/skills/common/common-llm-security/SKILL.md · GitHub

common-llm-security skillA

Name: common-llm-security
Author: hoangnguyen0403

This file is byte-identical to the first copy the registry indexed. Same content hash, same audit grade.

common-llm-security is agent-read markdown (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..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# 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](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. |
…

Read the whole file at its exact version.

How to install

Latest version

mdr add hoangnguyen0403/agent-skills-standard/common-llm-security@git:20260821.b9b1ba0

Exact content

mdr add hoangnguyen0403/agent-skills-standard/common-llm-security@sha256:eea5bf8560c3790d

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

[![mdr](https://markdownregistry.com/badge/art_kuw7ftvz5sj6tfyx.svg)](https://markdownregistry.com/a/art_kuw7ftvz5sj6tfyx)

0 badge views in 30 days

Versions

version	committed	commit	size	audit
git:20260821.b9b1ba0 latest	2026-08-21	b9b1ba0	2,982 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Deterministic, no model, same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (2982 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

hoangnguyen0403/agent-skills-standard · 571 stars · license MIT · pushed 2026-09-24 · branch develop

API

GET https://markdownregistry.com/api/v1/artifacts/art_kuw7ftvz5sj6tfyx
GET https://markdownregistry.com/api/v1/resolve?ref=hoangnguyen0403/agent-skills-standard/common-llm-security
GET https://markdownregistry.com/api/v1/blob/eea5bf8560c3790dc6af0a8cafe8b9455542a969316ae5bff26b2dc58877dcf3

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from hoangnguyen0403/agent-skills-standard

caveman-commit skill

hoangnguyen0403/agent-skills-standard · .agents/skills/caveman-commit/SKILL.md · Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning…

git:20260509.3e36716 · audit A · 571 stars

caveman-compress skill

hoangnguyen0403/agent-skills-standard · .agents/skills/caveman-compress/SKILL.md · Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens…

git:20260509.3e36716 · audit A · 571 stars

caveman-review skill

hoangnguyen0403/agent-skills-standard · .agents/skills/caveman-review/SKILL.md · Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment…

git:20260509.3e36716 · audit A · 571 stars

caveman skill

hoangnguyen0403/agent-skills-standard · .agents/skills/caveman/SKILL.md · Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical…

git:20260509.3e36716 · audit A · 571 stars

common-architecture-diagramming skill

hoangnguyen0403/agent-skills-standard · .agents/skills/common/common-architecture-diagramming/SKILL.md · Draw architecture diagrams as editable draw.io files with a fixed house style, C4 levels, and evidence-tagged shapes…

git:20260913.58fa467 · audit A · 571 stars

common-best-practices skill

hoangnguyen0403/agent-skills-standard · .agents/skills/common/common-best-practices/SKILL.md · Enforce SOLID principles, guard-clause style, function size limits, and intention-revealing naming across all…