OrionAIDev

Secure Plugin Installer — Security skill for Claude Code

Security community

Audit and gate third-party Claude Code plugins / OpenClaw skills before enabling them: capability enumeration, categorised pattern scanning, commit pinning, hash-chained trust ledger, per-MCP-server a.

How to install Secure Plugin Installer

This entry records only its repository, not the path inside it, so there is no exact command to give. Open OrionAIDev/secure-plugin-installer and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Secure Plugin Installer does

Alternatives in Security

Pocketpaw — Your AI agent in 30 seconds 775 ★
Openclaw Ops — OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans 225 ★
Amazon Skills — Free AI agent skills for Amazon sellers— keyword research, competitor analysis, listing audit & more 127 ★

README

Secure Plugin Installer

Cross-platform skill for auditing and gating third-party packages — **Claude Code plugins** (sourced from GitHub or any git-clonable URL) and **OpenClaw / ClawHub skills** (typically installed as plain directories under `/opt//workspace/skills/`).

This document is the **comprehensive reference** for humans. The companion [`SKILL.md`](SKILL.md) is a compact agent-facing trigger that describes the workflow at a high level; agents (Claude Code, OpenClaw, etc.) read it to decide when and how to invoke the installer. If something is brief in SKILL.md, the long-form explanation lives here.

What this is
When this is invoked
Quickstart (end-user examples)
What "install" means in each profile
The 6-step workflow
Trust ledger
Threat model — what this catches and doesn't
Architecture
Required dependencies
Install destinations and workspace layout
Backup, rollback, version comparison, and collision policy
Operational notes
Known limitations and open work

What this is

A guarded install pipeline for third-party packages whose code will run inside your agent's privileges (Claude Code or OpenClaw). Five layers, each independently useful:

Layer	What it does	Stops
Hardened clone	`git -c core.symlinks=false clone --depth=1 --no-tags --no-hardlinks`	Filesystem-traversal attacks via malicious symlinks; pollution of source repos via hardlinks
Capability enumeration	Parses declared hooks / MCP servers / postinstall scripts / permissions / build steps	Surfaces every auto-executing or privi