Vulnhunter Run logo

Vulnhunter Run

Community
nealbridges
vulnhunter-run

Unattended VulnHunter operator. Clone a repo, run the vulnhunt skill with this harness's own tools and subagents, then write and check the scan manifest. Does not call a model SDK and does not name a harness.

Overview

Publishernealbridges
RepositoryVulnHunter
Skill namevulnhunter-run
Stars
701
Forks
112
Bundled files
Instructions only
LicenseApache-2.0
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Vulnhunter Run 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/nealbridges/VulnHunter/tree/main/vulnhunter-run
  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/nealbridges/VulnHunter.git /tmp/VulnHunter
mkdir -p .claude/skills
cp -r /tmp/VulnHunter/vulnhunter-run .claude/skills/vulnhunter-run
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vulnhunter Run 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 Vulnhunter Run 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 Vulnhunter Run 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.

VulnHunter operator

You are the operator, not the hunter. The hunt methodology lives in the vulnhunt skill. Your harness runs that skill with its own model, tools, and subagents. You only sequence the steps and refuse to improvise when a step fails.

Install into the harness that is running you

When asked to install these skills, run install.sh from the repository root. Do not guess a directory.

  • If GROK_HOME is set, skills go to $GROK_HOME/skills and the agent file goes to $GROK_HOME/agents. Do not write to ~/.grok when GROK_HOME is a different directory.
  • Otherwise use the skills directory and the agents directory this harness scans. Do not use ~/.claude/skills unless this process is Claude Code.
  • The same install.sh writes vh to ~/.local/bin unless VULNHUNT_BIN_DIR is set. vh is what later steps call. It is not python3 -m vh from some other checkout.
bash
VULNHUNT_SKILLS_DIR="$GROK_HOME/skills" \
VULNHUNT_AGENTS_DIR="$GROK_HOME/agents" \
./install.sh

Omit GROK_HOME from that command when it is unset, and pass this harness's own two directories instead.

The vh commands do not talk to a model.

Steps

  1. Clone. If the user gave a git URL, run vh clone <url> --dest <dir>. If they gave a checkout, use that directory and skip the clone.
  2. Hunt. Invoke the vulnhunt skill on that checkout. Use this harness's subagents for the phase fan-out the skill describes. Do not shell out to another product's agent CLI. Wait until the skill finishes.
  3. Results. Run vh find-results <checkout>. One directory must be printed. If none is printed, stop and say the hunt produced no results. Do not invent a results directory.
  4. Manifest. Run vh write-manifest <results-dir>, then vh validate-manifest <results-dir>. If validation fails, stop and report the error. Do not hand-edit the manifest to force a pass.
  5. Stop. Tell the user the results path and whether the manifest validated. Publishing and GitHub issue filing are separate; do them only when the user asked, and use git and gh directly. Do not claim an issue was filed unless gh printed the URL.

Headless lab use

A batch runner sets VULNHUNT_HOST_CMD to this harness's headless one-shot. That program receives the prompt file path as its last argument and writes its transcript to stdout. vh host <prompt-file> is the only launcher. There is no default command.

Frequently asked questions

What does the Vulnhunter Run AI skill do?

Unattended VulnHunter operator. Clone a repo, run the vulnhunt skill with this harness's own tools and subagents, then write and check the scan manifest. Does not call a model SDK and does not name a harness.

Why use Vulnhunter Run on TypingMind?

Because you install it once and use it with any model. Vulnhunter Run 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 Vulnhunter Run in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nealbridges/VulnHunter/tree/main/vulnhunter-run. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vulnhunter Run?

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 Vulnhunter Run?

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

Is the Vulnhunter Run AI skill free?

Yes. It is published on GitHub by nealbridges under the Apache-2.0 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 👇