Sveltekit Security Stinger logo

Sveltekit Security Stinger

Organization
legioncodeinc
sveltekit-security-stinger

Evidence-backed, read-only security audit of Svelte 4/5 and SvelteKit 2 apps, any stack. Versions vs advisories, load leaks, actions, remote functions, hooks, XSS, CSRF, adapters.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill namesveltekit-security-stinger
Stars
94
Forks
44
Bundled files
16
LicenseAGPL-3.0-or-later
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 16 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by legioncodeinc on GitHub. Read the source before you install it.

Installation

Install the Sveltekit Security Stinger AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/code-audit-tools/skills/sveltekit-security-stinger
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/legioncodeinc/vibe-coding-tools.git /tmp/vibe-coding-tools
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-tools/plugins/code-audit-tools/skills/sveltekit-security-stinger .claude/skills/sveltekit-security-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sveltekit Security Stinger in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sveltekit Security Stinger on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sveltekit Security Stinger is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SvelteKit Security Stinger

Designed and built by Legion Code Inc.

Where this skill's files are

Every path below (guides/, references/, scripts/) is relative to the folder that contains this SKILL.md. In Claude Code that folder is ${CLAUDE_SKILL_DIR}. If that text was not replaced with a real path, find the folder yourself (Glob for **/sveltekit-security-stinger/SKILL.md) and use it as the skill directory in every command.

Purpose

Audit a Svelte or SvelteKit codebase for security problems the way an attacker would approach it, and report each one with evidence a founder can act on. The skill is framework-deep and stack-agnostic: it works on any SvelteKit 2 app (any database, auth library, or host) and on plain Svelte + Vite SPAs. It produces contract-shaped findings for the Audit My Code run: installed versions matched against every published advisory for svelte, @sveltejs/kit, devalue and the official adapters, plus manual-review findings across the server and client boundary, form actions, +server endpoints, remote functions, hooks and the authorization model, XSS sinks, CSP, cookies, adapters, prerendering, and patterns common in AI-written Svelte code. It never changes the audited repository.

When to use

  • The Audit My Code orchestrator dispatches sveltekit-security-wasp-drone because intake.json.stacks lists svelte or sveltekit
  • "Security audit this SvelteKit app", "are my form actions protected", "do my remote functions check auth", "is my load function leaking data"
  • "Which SvelteKit or Svelte advisories affect us", "is our devalue version safe"
  • Reviewing a Svelte + Vite SPA for secrets in the bundle and XSS sinks

When not to use

  • The repository's own stack-specific gate (SvelteKit with Neon, WorkOS, Stripe, Vercel, Doppler, GoHighLevel) before a commit: security-stinger, which also remediates
  • Secrets in git history, generic dependency triage, webhook signature checks, database row-level security: security-wasp-drone generic pass (security-stinger, armed report-only)
  • React or Next.js code: react-security-stinger or nextjs-security-stinger; back ends in other languages: polyglot-security-stinger
  • Fixing the findings: this skill is report-only; remediation planning belongs to the mario tier
  • A live, external scan of a deployed site with no source: web-security-posture-stinger

Procedure

  1. Read the run contract (audit-my-code-stinger/references/audit-contract.md) and intake.json. Your scope is the stack paths for svelte and sveltekit.
  2. Follow guides/00-scoping-and-version-check.md: classify each path, check advisory freshness, run scripts/sveltekit_audit_scan.py, review its version findings, and build the reading list.
  3. Follow guides/01-server-client-boundary-and-load-exposure.md: public env names, universal loads, server load returns, remote queries, shared state.
  4. Follow guides/02-actions-endpoints-remote-functions.md: build the endpoint table and check authorization, object ownership, validation, and CSRF for every surface.
  5. Follow guides/03-hooks-and-authorization-model.md: write the auth model, check identity, handle coverage (including remote functions), layout-only and client-only guards, server fetch, errors, redirects.
  6. Follow guides/04-xss-csp-and-cookies.md: every HTML sink, markdown pipeline, template-pattern advisory input, CSP, cookies, token storage.
  7. Follow guides/05-config-adapters-and-prerender.md: adapter and host, prerender, adapter-node headers, Vercel ISR, platform env, service worker.
  8. Follow guides/06-writing-findings.md: write findings-sveltekit-security-wasp-drone.jsonl, metrics-sveltekit-security-wasp-drone.json, and the notes file in 02-security/, validate them, and return the verdict, counts by severity, and every coverage cap.

Throughout: no finding without evidence; possible never above medium; redact secrets to the first 4 characters plus ****; never run installs, builds, or servers in the audited repository.

References map

PathLoad when
references/REFERENCE.mdStart of every run: file map, scanner interface and outputs, finding example
references/check-catalog.mdGuides 01 to 05: each check's detection, confirmation, severity, code pair, refs
references/detection-patterns.mdBefore each guide's manual read: tested ripgrep commands
references/advisory-table.mdGuide 00, and explaining a version finding
references/severity-guide.mdAssigning severity and confidence; guide 06
references/research/distilled-sveltekit-security.mdVerifying a claim, resolving a conflict, checking a thin spot
Source research archive (not shipped with the plugin)Source-repository only; the shipped distillation summarizes it, do not require it
scripts/sveltekit_audit_scan.pyOnce per run in guide 00
scripts/advisories.jsonData for the scanner; refresh when older than 30 days

Related drones and stingers

  • sveltekit-security-wasp-drone - The paired agent in this pack; the orchestrator dispatches it with this skill.
  • audit-my-code-stinger - The run orchestrator and the contract this skill writes against.
  • security-stinger (core) - Stack-specific Ship Gate security pass for SvelteKit with Neon, WorkOS, Stripe, Vercel, Doppler; the generic security pass in Audit My Code runs it report-only beside this skill.
  • react-security-stinger, nextjs-security-stinger, polyglot-security-stinger (this pack) - Framework-deep passes for other stacks in a monorepo.
  • svelte-stinger in web-development-tools (confirm installed) - Svelte 5 and SvelteKit 2 language and runtime details when a finding's fix needs them.
  • dependency-audit-stinger (core) - Lockfile and supply-chain work beyond framework advisories.

Critical Directive

  • You must read all files and context contained within your skill.
  • In the event your core knowledge does not provide sufficient guidance you must make every attempt to search the internet, related knowledge base documentation files, and other available resources to supplement your knowledge prior to proceeding with your task.
  • Additional related skills can be found here:
    • audit-my-code-stinger - Audit My Code orchestrator, tiers, routing, and the shared output contract.
    • security-stinger - Generic and stack-specific security pass; first gate of the Ship Gate in development work.
    • svelte-stinger - Svelte 5 runes, SvelteKit 2 load functions, form actions, and remote functions.

Designed and built by Legion Code Inc. Licensed under AGPL-3.0-or-later.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sveltekit Security Stinger AI skill do?

Evidence-backed, read-only security audit of Svelte 4/5 and SvelteKit 2 apps, any stack. Versions vs advisories, load leaks, actions, remote functions, hooks, XSS, CSRF, adapters.

Why use Sveltekit Security Stinger on TypingMind?

Because you install it once and use it with any model. Sveltekit Security Stinger is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sveltekit Security Stinger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/code-audit-tools/skills/sveltekit-security-stinger. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sveltekit Security Stinger?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sveltekit Security Stinger?

As many as you like. As long as a model supports skills, you can use Sveltekit Security Stinger with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sveltekit Security Stinger AI skill free?

Yes. It is published on GitHub by legioncodeinc under the AGPL-3.0-or-later license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇