Kerberos Exposure Audit logo

Kerberos Exposure Audit

Organization
zero-lab-ai
kerberos-exposure-audit

Audits supplied sanitized Kerberos governance evidence for policy, protection, monitoring, and evidence-handling exposure without contacting live systems. Use when reviewing a defensive Kerberos evidence package or assessing identity-control coverage.

Overview

Publisherzero-lab-ai
Repositoryskills
Skill namekerberos-exposure-audit
Stars
232
Forks
14
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by zero-lab-ai on GitHub. Read the source before you install it.

Installation

Install the Kerberos Exposure Audit 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/zero-lab-ai/skills/tree/main/plugins/identity-security/skills/kerberos-exposure-audit
  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/zero-lab-ai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/identity-security/skills/kerberos-exposure-audit .claude/skills/kerberos-exposure-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kerberos Exposure Audit 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 Kerberos Exposure Audit 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 Kerberos Exposure Audit 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.

Kerberos exposure audit

Use this skill only for passive review of an already-supplied, sanitized evidence package. It is an evidence audit, not discovery, validation, or authorization.

When to Use

  • Reviewing a defensive Kerberos evidence package or assessing identity-control coverage.
  • Use only within explicit authorization and the stated rules of engagement.

When NOT to Use

  • Do not treat this skill as permission to access, test, or change a target.
  • Do not convert missing evidence into a clean result or a stronger claim.

Boundary

Never query, authenticate to, or contact a live system. Never request, forge, replay, crack, decode, extract, or use tickets, credentials, secrets, or session material. Never enumerate live identities, services, realms, hosts, or addresses. Never coerce authentication, build an attack path, or provide commands, scripts, queries, tool syntax, payloads, or configuration bodies.

Reject raw or encoded ticket material, ticket-derived usable digests, hashes, session keys, passwords, secrets, service-principal strings, and real account, domain, realm, host, or address values. Keep diagnostics generic and never quote rejected content.

Workflow

  1. Accept only opaque IDs and 64-character lowercase hexadecimal digests.
  2. Record the engagement cutoff, closed policy, sanitized snapshot receipt, and opaque directory and scope references.
  3. Inventory only supplied subjects: identity, service identity, trust boundary, policy scope, or directory control. Do not discover new subjects.
  4. Create exactly one coverage cell for every subject and each policy- required Kerberos control dimension.
  5. Keep configuration, control effectiveness, freshness, and observed result as independent tracks. Do not infer one track from another.
  6. Bind every current claim to the exact subject, snapshot and digest, scope, directory reference, policy and digest, control and fingerprint, and window.
  7. Accept evidence only when it is supplied-passive, sanitized, inside its own validity window, no later than the cutoff, eligible, and in retained custody.
  8. Keep policy, configuration, control assurance, telemetry configuration, telemetry health, and result observation roles separate.
  9. Treat event absence as not-observed only when exact current telemetry configuration and healthy telemetry evidence support that same cell.
  10. Use not-applicable only with a closed reason and exact current policy evidence. Never use it to remove a difficult subject or dimension.
  11. Record each observed exposure as one immutable open finding. This ledger cannot close findings or claim remediation completion.
  12. Record only defensive handoffs for assessment review, evidence refresh, or remediation review. A handoff grants no authority.

Interpretation rules

  • complete-no-observed-exposure means every applicable cell has current exact evidence and no exposure was observed. Exact policy-backed non-applicability does not create a material unknown. This aggregate does not mean secure.
  • complete-with-exposure means at least one current exact observation is present and has an open finding.
  • material-unknowns means one or more material tracks are unknown, unavailable, or indeterminate.
  • stale means historical evidence cannot support a current claim.
  • incomplete means the required coverage matrix is not complete.

Report

Return the aggregate, state counts, open finding IDs, defensive handoffs, and generic conflict codes. Keep opaque references opaque. Do not reconstruct or describe operational identity values from the evidence package.

Rationalizations to reject

  • “A passive check is harmless against production.” Contact is still outside this skill; use only supplied evidence.
  • “The ticket is sanitized enough.” Ticket bodies and usable derivatives do not belong in this ledger.
  • “Policy says the control exists.” Policy evidence cannot substitute for configuration or effectiveness evidence.
  • “Configuration proves visibility.” Telemetry configuration is not healthy collection or an exact result observation.
  • “No event means no exposure.” Absence is meaningful only with current, healthy, complete telemetry evidence for the exact cell.
  • “The label did not change.” Snapshot, policy, or control fingerprint drift invalidates prior claims.
  • “We can close the finding here.” This ledger preserves open observations; later remediation belongs in a separately evidenced post-change record.
  • “The handoff approved action.” Handoffs transfer defensive work only.

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 Kerberos Exposure Audit AI skill do?

Audits supplied sanitized Kerberos governance evidence for policy, protection, monitoring, and evidence-handling exposure without contacting live systems. Use when reviewing a defensive Kerberos evidence package or assessing identity-control coverage.

Why use Kerberos Exposure Audit on TypingMind?

Because you install it once and use it with any model. Kerberos Exposure Audit 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 Kerberos Exposure Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zero-lab-ai/skills/tree/main/plugins/identity-security/skills/kerberos-exposure-audit. 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 Kerberos Exposure Audit?

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 Kerberos Exposure Audit?

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

Is the Kerberos Exposure Audit AI skill free?

Yes. It is published on GitHub by zero-lab-ai 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 👇