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 GoldenWing-360/claude-security-skills --skill llm-app-securitygit clone --depth 1 https://github.com/GoldenWing-360/claude-security-skillsWrote 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/goldenwing-360/claude-security-skills/llm-app-security)<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/llm-app-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/llm-app-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/goldenwing-360/claude-security-skills/llm-app-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/llm-app-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00088 | $0.02104 |
| Opus 5 | $0.00044 | $0.01052 |
| Sonnet 5 | $0.00018 | $0.00421 |
| Haiku 4.5 | $0.00009 | $0.00210 |
Grade A, and why
llm-app-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 11d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM App Security
The prompt and the tools are one layer of the story. This skill covers the other layer: the operational side of running an LLM-powered feature in production. The threats are mostly mundane (abuse, cost, leak, compliance), the controls mostly familiar from API security, applied to a substrate that has new failure modes.
Companion to prompt-injection-defense (prompt layer) and ai-agent-guardrails (tool layer).
When to invoke
- Designing or reviewing an LLM feature before public launch
- Investigating unusual API spend or 429s
- Handling an abuse complaint ("your AI told a user to ...", "your AI leaked ...")
- After a model-provider security advisory
- Periodic re-review of an existing LLM product surface
The OWASP LLM Top 10 — practical mapping
Walk these against your app. Most issues fall under one of these.
| ID | Issue | Practical control |
|---|---|---|
| LLM01 | Prompt injection | See prompt-injection-defense |
| LLM02 | Insecure output handling | Treat model output as untrusted: escape, sanitize, validate before acting |
| LLM03 | Training-data poisoning | Mostly upstream; pick reputable providers, version-pin |
| LLM04 | Model DoS | Per-user/IP rate limit; cost cap; max-tokens cap; timeout |
| LLM05 | Supply chain | Pin SDK versions, audit MCP/plugin packages, scan deps |
| LLM06 | Sensitive information disclosure | PII scrubbing pre-context; output review; allowlist what the model can fetch |
| LLM07 | Insecure plugin / tool design | See ai-agent-guardrails |
| LLM08 | Excessive agency | Narrow tool scope; human-in-loop for high-tier actions |
| LLM09 | Overreliance | UI disclosures; show provenance for facts; gate medical/legal/financial advice |
| LLM10 | Model theft / prompt theft | Treat the system prompt as a secret (not strong, but reduces casual leakage) |
Rate limiting and cost caps
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.
- 11d ago First seen · 162 lines · 88 tokens per session scan A d94759391447
llm-app-security is a skill published in the GitHub repository GoldenWing-360/claude-security-skills (17 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 2,104 once invoked, about $0.0004 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
ux-audit
Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sweep that didn't interact terminates with verdict 'Incomplete'. Walks threads, exercises every element, runs the…
tanstack-start
Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 +…
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…
product-showcase
Generate a comprehensive marketing website for a web app — multi-page with real screenshots, animated GIF walkthroughs, feature deep-dives, and workflow demonstrations. Browses the running app, captures screens and sequences, and produces a deployable site that actually teaches people what the product does. Especially…
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
cloudflare-api
Hit the Cloudflare REST API directly for operations that wrangler and MCP can't handle well. Bulk DNS, custom hostnames, email routing, cache purge, WAF rules, redirect rules, zone settings, Worker routes, D1 cross-database queries, R2 bulk operations, KV bulk read/write, Vectorize queries, Queues, and fleet-wide…