skillpack

Skill · GitHub · ★ 1.2k · graded 2026-10-22Source linked

Pack and deploy local AI agents for your team in minutes

No outside reports on file

Skillpack can help deploy agents quickly, but agents run with full access to local files and network unless you actively restrict them, so only use skills from trusted sources and review permissions carefully.

Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Skillpack helpful?

What it can access

Local filesReads & writes local foldersREVIEW
Command executionNo shell command runner notedLOW
Network reachConnects to outside service APINOTED
CredentialsRequires API key or tokenREVIEW
Package sourceGitHub (CreminiAI/skillpack)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/CreminiAI/skillpack ↗

All setup options ↓

Check this skill Watch it in my stack Compare README badge View project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-22.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Skillpack

Skillpack helps you package and deploy AI agents (smart programs that can take actions) for teams quickly. It appears designed to bundle local AI agents with their settings and tools so they're ready to run right away.

Who it’s for

Teams building or running multiple AI agents who want an easier way to set up and share them. Developers who need to move AI agents between computers or team members.

Alternatives

LangChain: Framework for building and chaining AI applications
CrewAI: Tool for creating multi-agent teams with task workflows
Hugging Face Spaces: Platform to deploy and share AI models and agents
OpenAI GPT Store / Custom GPTs: Pre-built AI agents with limited permissions

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README. The GitHub repository (https://github.com/CreminiAI/skillpack (opens external site)) should have installation and setup instructions specific to this tool.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

34/100

GitHub stars: 1.2k
Listing last refreshed: 2026-10-30

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

Access to local files: AI agents can read files on your computer, including sensitive documents or credentials stored nearby
Network requests: Deployed agents may contact outside servers, potentially leaking your data or agent behavior to the internet
Prompt injection: Malicious prompts hidden in files or user input could trick the AI into running unintended actions
No built-in sandboxing: The tool may run agents with full permissions to access whatever the host user can access
Supply chain: Downloaded skill packs from untrusted sources could contain harmful code disguised as AI instructions

How to lower the risk

Least-privilege permissions

Run agents under a limited user account with minimal file access
Restrict which folders agents can read or write

Network isolation

Use firewalls to limit where agents can send data
Audit outbound connections from deployed agents

Monitoring

Log all agent actions and file access
Review what data agents are processing

Red flags to watch for

Skills from unknown authors or with unclear purposes
Agents requesting access to sensitive folders like password managers
Unusual network activity during agent runs

Questions

How do I install Skillpack?

Skillpack does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/CreminiAI/skillpack.

Are there security reports about Skillpack?

No reports found for this package in our research (last checked 2026-10-30). Skillpack currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include access to local files, network requests, prompt injection.

Is Skillpack actively maintained?

Skillpack has 1.2k GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/CreminiAI/skillpack before pinning it in production.

What are alternatives to Skillpack?

Notable alternatives to Skillpack include LangChain (Framework for building and chaining AI applications), CrewAI (Tool for creating multi-agent teams with task workflows), Hugging Face Spaces (Platform to deploy and share AI models and agents), OpenAI GPT Store / Custom GPTs (Pre-built AI agents with limited permissions). You can also compare Skillpack side by side with other skills in the Related tools section on this page.

Maintain or use Skillpack? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

GitHub README Markdown:

markdown

[![AgentArmorHQ Risk Grade for Skillpack](https://agentarmorhq.com/api/badge/creminiai-skillpack)](https://agentarmorhq.com/skills/creminiai-skillpack)

HTML embed:

html

<a href="https://agentarmorhq.com/skills/creminiai-skillpack"><img src="https://agentarmorhq.com/api/badge/creminiai-skillpack" alt="AgentArmorHQ Risk Grade for Skillpack" height="20" /></a>

Terminal check:

terminal

curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "creminiai-skillpack"

Share with your security lead

Need sign-off to use skillpack? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: skillpack
- **Listing URL:** https://agentarmorhq.com/skills/creminiai-skillpack
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.2k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** Reads & writes local folders
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (CreminiAI/skillpack)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/CreminiAI/skillpack
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type: AI agent skill
Publisher: CreminiAI
Source code: github.com/CreminiAI/skillpack
Est. context load: ~50 tokens idle · ~450 tokens when active (on-demand skill)
Popularity: 1.2k GitHub stars
Last updated: 2026-10-30
Last graded: 2026-10-22

Community

Discussions for Skillpack

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Skillpack helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude