AGENT SKILL

skillgate-gov

Supply-chain governance for OpenClaw skills: scan, assess, quarantine/restore.

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

01 前言 Front Matter

name
skillgate-gov
metadata
{ "openclaw": { "emoji": "🛡️", "homepage": "https://github.com/skillgatesecurity/openclaw-skillgate", "requires": { "bins": [ "node", "npm" ] } } }
description
Supply-chain governance for OpenClaw skills: scan, assess, quarantine/restore.

03 SKILL.md 正文

SkillGate (Governance)

This skill teaches OpenClaw how to run SkillGate against a skills directory, generate evidence, and quarantine risky skills.

Quick Start (recommended)

We intentionally avoid global installs (npm i -g) to reduce supply-chain risk. Use a pinned version via npx for deterministic behavior.

# Scan current workspace (read-only by default)
npx --yes @skillgate/openclaw-skillgate@0.1.3 gov_scan .

# Show a human-readable explanation for a finding
npx --yes @skillgate/openclaw-skillgate@0.1.3 gov_explain <EVIDENCE_JSON_PATH>

Provenance / How to verify what you run

# Verify package metadata
npm view @skillgate/openclaw-skillgate@0.1.3 name version license repository
npm view @skillgate/openclaw-skillgate@0.1.3 dist.tarball dist.integrity

# Optional: verify GitHub release & source
# Repo: https://github.com/skillgatesecurity/openclaw-skillgate

This package is published under the official @skillgate scope and built/released via GitHub Actions.

Permissions & Filesystem scope

  • Network: not required for scanning local files (except fetching the npm package on first run).
  • Default mode: read-only scan of the given directory.
  • Writes (only when you explicitly run quarantine/restore commands):
    • creates/updates evidence outputs under a local folder (e.g. .skillgate/ or the specified output path)
    • may quarantine a skill by moving/marking files within the target directory you pass in

It does not require secrets (no tokens/keys) and does not modify system-wide settings.

OpenClaw Plugin Commands

Once loaded as an OpenClaw plugin, these slash commands become available:

# scan all skills for risks (default: HIGH+)
/gov scan

# scan with all findings including LOW/INFO
/gov scan --all

# quarantine a specific skill
/gov quarantine <skillKey>

# restore a quarantined skill
/gov restore <skillKey>

# explain why a skill was flagged
/gov explain <skillKey>

# show governance status
/gov status

Risk Levels

Level Auto Action Description
CRITICAL Quarantine Shell injection, supply-chain attacks
HIGH Disable Dangerous patterns, external downloads
MEDIUM Warn Risky but not immediately dangerous
LOW/INFO Log Informational only

Local Development (optional)

If you prefer a local dependency instead of npx:

npm i -D @skillgate/openclaw-skillgate@0.1.3
npx gov_scan .

Notes

Use this as the standard operating procedure for Skill supply-chain reviews.

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0