rolecraft
Install skills — from local folders, GitHub repos, GitLab projects, or SSH git URLs - Manage skills — list, update, remove, and…
Examining code for the line that is wrong
What it does
Install and manage AI agent skills across 86 agents (26 verified) with a single command. Zero dependencies. No registry required.
What it can touch
Includes 160 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: .github/scripts/release-prep.sh, .github/scripts/release-prep.test.js, benchmark/install-speed.js, bin/rolecraft.js….
Mentions an outside service
The instructions point your AI at these sites or APIs. Anything it sends there leaves your computer.
How we know
Web addresses in the SKILL.md, excluding GitHub and documentation sites: gitlab.com.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
Asks for administrator rights
Some of its commands use sudo or "run as administrator". Those can change anything on your computer.
How we know
Seen in its code. Read 2026-10-05, commit 42dab7a.
12 smaller things worth knowing
Refers to a credentials file (SSH keys, cloud logins, tokens); Contains commands that delete or overwrite; Edits your shell start-up file; Downloads a script and runs it in one step, unread; and more. Usually legitimate — listed so nothing is hidden.
How we know
Refers to a credentials file (SSH keys, cloud logins, tokens) — RELEASE.md line 16; Contains commands that delete or overwrite — docs/migration-from-skills.md line 74; Edits your shell start-up file — docs/reference.md line 374; Downloads a script and runs it in one step, unread — docs/security.md line 65; Tells your AI to ignore its other instructions — docs/security.md line 126; Refers to a credentials file (SSH keys, cloud logins, tokens) — docs/security.md line 127. Read 2026-10-05, commit 42dab7a.
RELEASE.md, line 16 ↗docs/migration-from-skills.md, line 74 ↗docs/reference.md, line 374 ↗docs/security.md, line 65 ↗docs/security.md, line 126 ↗docs/security.md, line 127 ↗No serious risk pattern found
Launch7’s automated check read all 224 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-05, commit 42dab7a by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to rolecraft-sh/rolecraft: 2026-10-03 (2 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 160 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end