Atlas / Skills / alvinunreal / Cartography

CartographyBLOCK

skills/alvinunreal/cartography

Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks

Verdict
BLOCK
Grade
F
Trust score
40 /100
Version
1.0
Hosts
6 documented
License
MIT
Stars
9,675
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

✨ oh-my-opencode-slim ✨

Six divine beings emerged from the dawn of code, each an immortal master of their craft,awaiting your command to forge order from chaos and build what was once thought impossible.

Opencode Multi Agent Suite · Mix any models · Auto delegate tasks by Boring Dystopia Development

svgdiagram.ai · Turn your notes into clean, editable SVG diagrams

English | 简体中文 | 日本語 | 한국어 | فارسی

✦ ✦ ✦

What's This Plugin

oh-my-opencode-slim is an agent orchestration plugin for OpenCode. It includes a built-in team of specialized agents that can scout a codebase, look up fresh documentation, review architecture, handle UI work, and execute well-scoped implementation tasks under one orchestrator.

The main idea is simple: inst

Read from source at commit 30e06f377171OBSERVED · 2026-10-20
Advertisement
02

Install

Commands as the repository documents them. They are shown, not run.

npm i -g greptile
git clone https://github.com/alvinunreal/oh-my-opencode-slim.git ~/repos/oh-my-opencode-slim
git clone https://github.com/alvinunreal/oh-my-opencode-slim.git ~/repos/oh-my-opencode-slim
git clone https://github.com/alvinunreal/oh-my-opencode-slim.git ~/repos/oh-my-opencode-slim
git clone https://github.com/alvinunreal/oh-my-opencode-slim.git ~/repos/oh-my-opencode-slim
git clone https://github.com/alvinunreal/oh-my-opencode-slim.git ~/repos/oh-my-opencode-slim
03

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
codexmentioned
copilotmentioned
cursormentioned
gemini-climentioned
openclawmentioned
04

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: cli-review
description: >
  Runs a Greptile CLI review for the current local branch, installing or authenticating the CLI
  when needed, then summarizes JSON findings for the user. Use when the user wants Greptile
  feedback before opening a PR, outside a hosted PR review flow, or directly from a local checkout.
license: MIT
metadata:
  author: greptileai
  version: "1.0"
allowed-tools: Bash(git:*) Bash(greptile:*) Bash(command:*) Bash(curl:*) Bash(npm:*)
---

# CLI Review

Run a Greptile review from the local checkout and summarize the findings.

## Instructions

### 1. Confirm repository context

Start from the current repository root:

```bash
git rev-parse --show-toplevel
```

If the command fails, tell the user that the Greptile CLI review must be run from a git repository.

### 2. Check for the Greptile CLI

Check whether `greptile` is installed:

```bash
command -v greptile
```

If it is missing, do not install it automatically. Ask the user for permission, then show the recommended install command:

```bash
npm i -g greptile
```

If npm is unavailable, offer the shell installer fallback:

```bash
curl -fsSL "https://greptile.com/cli/install" | sh
```

After installation, re-run `command -v greptile`.

### 3. Ensure authentication

Check the signed-in account:

```bash
greptile whoami
```

If the CLI reports that authentication is missing, run:

```bash
greptile login
```

Wait for the user to complete the login flow before continuing.

### 4. Run the review

Prefer JSON output:

```bash
greptile review --json
```

If JSON output is unsupported or fails with a usage error, fall back to:

```bash
greptile review --agent
```

Do not hide the raw command failure if both commands fail. Summarize the failing command and the next action the user needs to take.

### 5. Summarize results

Parse JSON output when available and report:

- Review status
- Number of findings
- Highest severity findings first
- Files that need edits
- Suggested next command or fix path

When output is plain text, preserve the same structure as much as possible. Keep the summary concise and focused on actionable findings.
05

Trust audit

BLOCKgrade F · trust 40/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryFAIL
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)FAIL
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (4 observation(s))
Network
declared (5 observation(s))
Shell
declared (3 observation(s))
Dependencies
not all pinned
Secrets in source
found

Findings (25)

HIGHInventory / provenance · inv.suspicious_name · CWE-1104
src/hooks/__snapshots__/cache-payload.snapshot.test.ts.snap
cache-payload.snapshot.test.ts.snap
Why it matters. member named after an attack tool
Fix. remove or justify
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.fa-IR.md:7
<p><i>شش موجود افسانهای از دل دنیای کد ظهور کردهاند؛ هرکدام استادی بیهمتا در تخصص خود،<br>آمادهاند تا به فرمان شما آشوب را به نظم تبدیل کنند و چیزهایی بسازند که روزی ناممکن به نظر میرسیدند.</i></p>
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.fa-IR.md:9
<p><b>مجموعه Multi-Agent برای OpenCode</b> · ترکیب آزادانه مدلها · واگذاری خودکار taskها</p>
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.fa-IR.md:10
<p><sub>ساختهشده توسط <b>Boring Dystopia Development</b></sub></p>
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.fa-IR.md:19
<a href="https://svgdiagram.ai"><b>svgdiagram.ai</b></a> <sub>· یادداشتهایتان را به نمودارهای SVG تمیز و قابلویرایش تبدیل کنید</sub>
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427
README.fa-IR.md:32
افزونه oh-my-opencode-slim یک Plugin برای هماهنگسازی و مدیریت Agentها در OpenCode است. این افزونه یک تیم داخلی از Agentهای تخصصی دارد که میتوانند Codebase را بررسی کنند، مستندات بهروز را پیدا کنند، مع
Why it matters. invisible characters in instruction text
Fix. strip non-printing characters
MEDIUMHard-coded secrets · secret.db_uri · CWE-798, CWE-321
src/utils/redact.test.ts:85
const dsn = 'postgres://deploy:[email protected]:5432/app';
MEDIUMHard-coded secrets · secret.db_uri · CWE-798, CWE-321
src/utils/redact.test.ts:210
'Subagent failed (sessionID: ses_5d4c3b): connection refused for postgres://deploy:hunter2@db';
MEDIUMHard-coded secrets · secret.db_uri · CWE-798, CWE-321
src/utils/redact.test.ts:274
'<task id="abc" state="running">text (sessionID: ses_9f8e7d) postgres://deploy:hunter2@db';
MEDIUMHard-coded secrets · secret.db_uri · CWE-798, CWE-321
src/utils/redact.test.ts:279
'<task id="[masked]" state="[masked]">text (sessionID: [masked]) postgres://deploy:...@db',
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
src/utils/redact.test.ts:41
const token = 'glpat-Abcdef1234567890123';
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
src/utils/redact.test.ts:97
const token = 'Z9xQ1w2e3r4t5y6u7i8o9p0a1s2d3f4g5h6j7';
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
src/utils/redact.test.ts:153
const secret = 'Q1w2e3r4t5y6u7i8o9p0a1s2d3f4g5h6j7k8l9z0'; // 40 chars
MEDIUMSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
.agents/skills/cli-review/SKILL.md:47
curl -fsSL "https://greptile.com/cli/install" | sh
LOWInventory / provenance · inv.hidden_file · CWE-1104
.all-contributorsrc
.all-contributorsrc
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.suspicious_name · CWE-1104
src/hooks/cache-payload.snapshot.test.ts
cache-payload.snapshot.test.ts
Why it matters. member named after an attack tool
Fix. remove or justify
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/hooks/image-hook.test.ts:25
const IMG_HASH = createHash('sha1').update(IMG_BYTES).digest('hex').slice(0, 8);
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/hooks/image-hook.ts:298
const hash = createHash('sha1').update(data).digest('hex').slice(0, 8);
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/skills/codemap/scripts/codemap.mjs:123
return createHash('md5').update(buffer).digest('hex');
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/skills/codemap/scripts/codemap.mjs:140
const hasher = createHash('md5');
LOWInsecure crypto · crypto.weak_random · CWE-327, CWE-338
src/cache-safety-tripwire.test.ts:84
'Date.now()/Math.random() compose a per-run temp token for install bookkeeping; it names local directories and never reaches the prompt prefix.',
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/config/loader.test.ts:78
fs.writeFileSync(path.join(worktree, '.git'), 'gitdir: ../../../.git');
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/hooks/absolute-path-rescue/index.test.ts:102
const dotted = `${os.tmpdir()}/__slim_missing_1143__/../../src`;
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/hooks/absolute-path-rescue/index.ts:33
import { log } from '../../utils/logger';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/hooks/apply-patch/index.ts:3
import { log } from '../../utils/logger';

Gates applied: no_behavioural_pass.

Audited 2026-10-20 · audit v0.4.1 · source sha 30e06f377171full audit observations/trust-audit/skill/alvinunreal__cartography.json · Report an issue / request a re-scan
06

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-2030e06f377171BLOCKF40first audit
07

Questions

What does the cartography — alvinunreal/oh-my-opencode-slim skill do?

Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks

Is cartography — alvinunreal/oh-my-opencode-slim safe to install?

No — not without reading the findings first. The audit graded it F (40/100) and found 6 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What can cartography — alvinunreal/oh-my-opencode-slim access on my machine?

The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: found — see the findings.

Which assistants does cartography — alvinunreal/oh-my-opencode-slim work with?

Its documentation mentions claude-code, codex, copilot, cursor, gemini-cli and openclaw. 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 (30e06f377171), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Add this badge to your README

Shows this page's audit result and links back to it. It updates when the audit does.

ModelsAtlas audit badge

Markdown
[![ModelsAtlas audit: Cartography](https://modelsatlas.com/skills/alvinunreal/cartography/badge.svg)](https://modelsatlas.com/skills/alvinunreal/cartography/)

Not your listing, or something out of date? Claim or update your listing.

Advertisement