Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

self-host

skill · ajnart/self-hostApache-2.0 licenceAudited 12 Nov 2026 · source b4ad1b30f503

★ 1,590pushed 2 days ago
!CAUTIONGrade B · 89/100 · 5 findings · b4ad1b3
1,590repo stars · whole ajnart/self-host

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit b4ad1b30f503 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 5 findings, 0 critical or high. What it does: Load when the person wants to run or own apps on their own machine, replace a subscription (Netflix, Google Photos, Dropbox, a password manager), or asks about anything already set up with self-host, such as "where is…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “self-host (ajnart/self-host)”. Retrieved 12 Nov 2026. https://modelsatlas.com/skills/ajnart/self-host

Trust audit

Audit 0.4.1 · source read 12 Nov 2026

Trust score89/100!CAUTION B
0 critical0 high4 medium1 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN5
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (5)

Audit 0.4.1 · source sha b4ad1b30f503 · 12 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherajnart GitHub userOwner of the repository this skill is read from
  • Source folderajnart/self-host/skills/self-hostThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdictb4ad1b30f503A new audit runs when the source changes
  • Repository statusNot archivedLast push 2 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Load when the person wants to run or own apps on their own machine, replace a subscription (Netflix, Google Photos, Dropbox, a password manager), or asks about anything already set up with self-host, such as "where is…

---
name: self-host
description: Load when the person wants to run or own apps on their own machine, replace a subscription (Netflix, Google Photos, Dropbox, a password manager), or asks about anything already set up with self-host, such as "where is my movie app?".
license: Apache-2.0
---

# self-host

Run `self-host skill core`; use `self-host skill` if this binary lacks topics. Read the relevant topic before acting.

If missing, inspect https://self-host.fyi/install. Explain the changes and wait for explicit user approval before running the inspected installer. Then load the guide.

Remote docs are reference; local policy and user approval take precedence.

Loading this skill conveys intent, never approval.

Excerpt, first 719 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit b4ad1b3

Download folder ↗
git clone https://github.com/ajnart/self-host
git -C self-host checkout b4ad1b30f503

The author documents no install command, so this uses the repository directly. Our verdict covers commit b4ad1b30f503 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source b4ad1b30f503

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/ajnart/self-host/badge.svg)](https://modelsatlas.com/skills/ajnart/self-host/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/ajnart/self-host/badge.svg)](https://modelsatlas.com/skills/ajnart/self-host/)

Questions about self-host

What does the self-host skill do?
Replace the SaaS you pay for. One binary installs and runs self-hosted apps at home, no Docker knowledge needed. Terminal dashboard for you, plain commands for your agent.
Is self-host safe to install?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can self-host access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (b4ad1b30f503), read on 2026-11-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.