Polyglot Security Stinger logo

Polyglot Security Stinger

Organization
legioncodeinc
polyglot-security-stinger

Deep security audit for Node servers, Python, Go, Rust, Rails, PHP, Spring, and .NET, plus secrets, dependencies, SAST, and CI. Read-only, writes Audit My Code findings.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill namepolyglot-security-stinger
Stars
94
Forks
44
Bundled files
37
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.

  • 37 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 Polyglot 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/polyglot-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/polyglot-security-stinger .claude/skills/polyglot-security-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Polyglot 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 Polyglot 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 Polyglot 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.

Polyglot 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 (for example with Glob for **/polyglot-security-stinger/SKILL.md) and use it as SKILL_DIR in every command.

Purpose

Audit the parts of a codebase that are not React, Next.js, or SvelteKit (those have their own pairs) for security weaknesses, ecosystem by ecosystem, and write the results in the Audit My Code contract shape so the brief can show them. It goes deeper than the core generic pass in security-stinger: one guide per ecosystem (Node.js servers, Python, Go, Rust, Ruby on Rails, PHP, Java and Kotlin with Spring Boot, .NET), each backed by a checklist, source and sink tables, ripgrep patterns, and vulnerable versus fixed code pairs, plus cross-cutting guides for secrets, dependency vulnerabilities, static analysis, CI/CD and infrastructure, and AI-generated code. It never changes the audited repository; tools run only in the throwaway copy, and anything that cannot run becomes a recorded coverage cap.

When to use

  • An /audit-my-code run at basic, full, or mario tier detects node-server, python, go, rust, ruby, php, java-kotlin, dotnet, or other in intake.json.stacks
  • "Security audit this Django / FastAPI / Flask / Go / Rails / Laravel / Spring / ASP.NET service"
  • "Check this monorepo's backend services, CI workflows, and Dockerfiles for security problems"
  • Any time the orchestrator needs to know which ecosystems a repository contains: scripts/detect_ecosystems.py returns the intake.json.stacks array

When not to use

  • React, Next.js, Svelte, or SvelteKit code: react-security-stinger, nextjs-security-stinger, sveltekit-security-stinger
  • Fixing the problems found: this pair reports only; remediation planning belongs to the mario tier's remediation Drone, and code changes to the owning engineering Drones
  • A Ship Gate pass on a branch before commit: security-stinger
  • Auditing a live third-party website from the outside: web-security-posture-stinger

Procedure

  1. Read audit-my-code-stinger/references/audit-contract.md and the arming line. Never write inside the audited repository.
  2. Run guides/00-scoping-and-ecosystem-detection.md: set up the workspace variables and the rgs helper, run scripts/detect_ecosystems.py on the copy, build the scope table, and mark paths owned by other Drones.
  3. For each stack in scope, run its ecosystem guide: 01 Node.js, 02 Python, 03 Go, 04 Rust, 05 Rails, 06 PHP, 07 Java and Kotlin, 08 .NET. Stack other gets the cross-cutting guides plus a manual read.
  4. Run the cross-cutting guides in order: 09 secrets, 10 dependencies, 11 static analysis, 12 CI/CD and infrastructure (when this Drone owns the infra files), 13 AI-generated code patterns.
  5. Run guides/14-writing-findings.md: write 02-security/findings-polyglot-security-wasp-drone.jsonl, metrics-polyglot-security-wasp-drone.json, and notes-polyglot-security-wasp-drone.md, raw output under 02-security/raw/polyglot/, and an ## Evidence section in the notes file.
  6. Validate with scripts/validate_findings.py, fix every error, then return the verdict, finding counts by severity, and every coverage cap.

References map

PathLoad when
references/cross-cutting/tool-commands.mdAlways: setup, the rgs helper, pinned tool commands, the fallback ladder, what to record when a tool cannot run
references/cross-cutting/manifest-to-stack.mdChecking or hand-classifying ecosystem detection
references/ecosystems/node-server.mdGuide 01
references/ecosystems/python.mdGuide 02
references/ecosystems/go.mdGuide 03
references/ecosystems/rust.mdGuide 04
references/ecosystems/ruby.mdGuide 05
references/ecosystems/php.mdGuide 06
references/ecosystems/java-kotlin.mdGuide 07
references/ecosystems/dotnet.mdGuide 08
references/cross-cutting/secrets-patterns.mdGuide 09, or triaging any secret hit
references/cross-cutting/dependency-triage.mdGuide 10, or deciding an advisory's severity
references/cross-cutting/static-analysis-rulesets.mdGuide 11
references/cross-cutting/ci-cd-infra.mdGuide 12
references/cross-cutting/ai-failure-patterns.mdGuide 13
references/cross-cutting/contract-output-rules.mdGuide 14, or any question about severity, confidence, or file shape
references/research/distilled-polyglot-security.mdVerifying a claim, or checking a known thin spot before asserting a framework default
Source research archive (not shipped with the plugin)Source-repository only; the shipped distillation summarizes it, do not require it
scripts/detect_ecosystems.pyGuide 00; also reusable by the orchestrator for intake.json.stacks
scripts/secrets_fallback.pyGuide 09 when gitleaks and trufflehog cannot run
scripts/validate_findings.pyGuide 14, before returning
scripts/test_detect_ecosystems.pyAfter changing the detector

Related drones and stingers

  • polyglot-security-wasp-drone - The paired agent in this pack; the orchestrator dispatches it with the list of ecosystems and paths.
  • audit-my-code-stinger - The orchestrator and the run contract this skill writes against.
  • security-stinger (core) - The generic security pass that runs beside this one in an audit; also the Ship Gate first pass for development work.
  • react-security-stinger, nextjs-security-stinger, sveltekit-security-stinger - The framework pairs that own JavaScript UI framework paths.
  • dependency-audit-stinger (core) - Deeper dependency-management workflows (Renovate, SBOM, provenance) beyond audit triage.
  • devops-stinger in platform-and-release-tools (confirm installed) - Docker and GitHub Actions implementation guidance when a fix is planned.

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 and the shared run contract.
    • security-stinger (core Wasp Nest skill, when installed) - Generic security pass that runs beside this one; Ship Gate first gate for development work.

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 Polyglot Security Stinger AI skill do?

Deep security audit for Node servers, Python, Go, Rust, Rails, PHP, Spring, and .NET, plus secrets, dependencies, SAST, and CI. Read-only, writes Audit My Code findings.

Why use Polyglot Security Stinger on TypingMind?

Because you install it once and use it with any model. Polyglot 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 Polyglot 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/polyglot-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 Polyglot 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 Polyglot Security Stinger?

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

Is the Polyglot 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 👇