Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

paint

skill · athevon/genjutsuNOASSERTION licenceAudited 29 Oct 2026 · source 7196f765fc11

★ 700pushed 23 days ago
!CAUTIONGrade B · 89/100 · 2 findings · 7196f76
700repo stars · whole athevon/genjutsu

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 7196f765fc11 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 2 findings, 0 critical or high. What it does: Paint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI).

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “paint (athevon/genjutsu)”. Retrieved 29 Oct 2026. https://modelsatlas.com/skills/athevon/paint

Trust audit

Audit 0.4.1 · source read 29 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high1 medium1 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 16,667 of 17,602 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, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesWARN2
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

MEDIUMPrivilege escalation / persistencereview.unsafe_action · SKILL.md
F-06 Privilege escalation / persistenceCWE-269 · CWE-250Layer L2
npx skills add https://genjutsu.athevon.dev -g
Why
It directs the agent to install external dependencies via the network without requiring the user's explicit approval in that code path.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts
LOWPrompt injectionreview.data_transfer · SKILL.md
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
any agent    npx skills add https://genjutsu.athevon.dev -g
Why
The pipeline stop condition instructs the agent to print an external installation command that downloads and installs the full genjutsu bundle over the network.
Fix
rewrite it so the instruction says plainly what it does, and asks the user before it acts

Audit 0.4.1 · source sha 7196f765fc11 · 29 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherathevon GitHub userOwner of the repository this skill is read from
  • Source folderathevon/genjutsu/skills/paintThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdict7196f765fc11A new audit runs when the source changes
  • Repository statusNot archivedLast push 23 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Paint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI).

---
name: paint
description: "Paint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI)."
allowed-tools: Bash, Read, Edit, Write, Grep, Glob, WebSearch, Artifact
---

# Paint - The Master Painter

> Paint a complete visual universe. Brainstorm first, design system second, implement third, audit last.
> This is NOT a quick beautifier - it's a full design pipeline.

---

## Voice

This skill speaks in two registers:

**During execution** - light ninja flair, signature, immersive. Short.
- "Brushing the color palette..."
- "Painting the hero with the unalloyed gold."
- "Setting the spacing tokens."

**In reports / final summaries / audit results** - plain, factual, dev-readable. Drop the flair entirely.
- "Done. Design system generated. Files: MASTER.md, tokens.css, theme.config.ts. 3 pages painted."
- No mystic prose, no metaphors. Just what changed, files touched, next step.

The flair lives at the intro and during work narration. The moment a result lands or a question gets asked, it's gone.

---

## /paint vs /cast

| | `/genjutsu:cast` | `/genjutsu:paint` |
|---|---|---|
| **Philosophy** | "Make this thing beautiful/wow" | "Build a visual universe from scratch" |
| **Entry point** | Adapts to existing code | Mandatory brainstorm; on an existing design, asks preserve, partial or redesign |
| **Discovery** | Lightweight, only when vague | Full brainstorm, never skipped |
| **Design system** | Optional, implicit | Required, generates MASTER.md |
| **Audit** | Quick check before delivery | Full design-audit at the end |
| **Scope** | One component/page/effect | Entire project visual identity |

`/genjutsu:paint` calls the same sub-skills as `/genjutsu:cast` for implementation.

A whole site or web app built from real material is the job of the third pipeline,
`/genjutsu:bunshin`: a team of subagents under one art director, with independent reviews
until only minor issues remain or the tier's round cap is reached. paint proposes it right after
the stack scan when the brief is that size, the stack is web or there is no project yet, and the
host can spawn subagents, and switches only on a yes.

---

## Iron Rules

1. **Never skip the brainstorm.** Not even if the user says "just make it look good." Especially then. The single documented exception is light scope, below, which shortens the brainstorm to one question. It never removes it. With nobody answering, see "When nobody is answering": the questions are answered from the brief, as assumptions.
2. **One question at a time during brainstorm.** Never bundle. The second question depends on the first answer.
3. **Never proceed without the theses validated.** Visual + interaction, both explicitly approved. The one exception is light scope, below: no visual identity is at stake there, so the interaction thesis alone is required - and it is still validated explicitly, never assumed. With nobody answering, see "When nobody is answering".
4. **Every design token comes from MASTER.md.** No magic numbers, no rogue hex values. On light scope, where no MASTER.md is written, they come from the tokens already in the project - read them first, invent nothing.
5. **Every animation respects the interaction thesis.** Timing, easing, forbidden patterns - no exceptions.
6. **Never install a dependency without asking.** With nobody answering, never install one (see "When nobody is answering").
7. **Work page by page, validate page by page.** Never try to do everything at once.
8. **The audit is not optional.** Phase 5 always runs, even if the user seems happy. On light scope it shortens to the quick check - thesis against code, reduced-motion, exit animation, 60fps - but it never disappears.
9. **Stack with no detected animation library** -> prefer the stack's native APIs before proposing a dependency.
10. **Animation library detected** (GSAP, Motion / Framer Motion, Lottie, Rive, etc.) -> respect the dev's choice. Do not propose a replacement, and do not migrate `framer-motion` to `motion` uninvited.
11. **Show, don't just describe.** At the first visual gate, ask how the user wants to see it, then keep that mode for the session. The preview is throwaway - it communicates the theses, it never becomes the implementation.

---

## Light scope - the one shortened path

`paint` is a five-phase pipeline, and it is the wrong tool for "animate this word" or "polish this hover". Those belong to `/genjutsu:cast`, which is the default entry point.

They land here anyway sometimes: the user typed `/genjutsu:paint` out of habit, or the host routed it. Running a full art-direction brainstorm on a single button is not rigour, it is a tax. Recognise the case and shorten, out loud.

**It is light scope when all three hold:**

- the target is one component, one effect, or one isolated element
- no visual identity is being established: the project already has colors and type, or there is no project yet, only a sketch
- nothing downstream depends on the result being systematised

If two or more fail, it is not light scope. Run the full pipeline and say in one line why.

**What changes:**

| Phase | Full | Light |
|---|---|---|
| 1 BRAINSTORM | five domains, one question at a time | **one question**, the least obvious one, then stop |
| 2 THESIS | visual + interaction, both validated | interaction thesis only, still validated |
| 3 DESIGN SYSTEM | generate MASTER.md and the stack token files | **skipped.** Read the tokens already in the project and use them. Write no MASTER.md. |
| 4 IMPLEMENT | page by page, validate page by page | the one component |
| 5 AUDIT | full design-audit sub-skill | the quick check: thesis against code, reduced-motion, exit animation, 60fps |

**Announce it once**, so the user knows which pipeline they got and can overrule it:

> "This is a single component, so I am running paint light: one question, no design system fi

Excerpt, first 6,000 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 7196f76

Download folder ↗
git clone https://github.com/athevon/genjutsu
git -C genjutsu checkout 7196f765fc11

The author documents no install command, so this uses the repository directly. Our verdict covers commit 7196f765fc11 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source 7196f765fc11

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/athevon/paint/badge.svg)](https://modelsatlas.com/skills/athevon/paint/)

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/athevon/paint/badge.svg)](https://modelsatlas.com/skills/athevon/paint/)

Questions about paint

What does the paint skill do?
Creative coding skills for Claude Code, claude.ai and Cowork. Motion, micro-interactions and design systems across Web (GSAP, Motion, Three.js, CSS), Android (Jetpack Compose) and Apple (SwiftUI). Proposes an interaction thesis you approve before it writes any code. Anti-AI-slop.
Is paint safe to install?
With care. The audit graded it B (89/100) and found 2 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can paint access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does paint work with?
Its documentation mentions claude-code, codex and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (7196f765fc11), read on 2026-10-29. 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.