← 返回
AI智能 中文

SkillGate Governance

Supply-chain governance for OpenClaw skills: scan, assess, quarantine/restore.
OpenClaw技能的供应链治理:扫描、评估、隔离/恢复。
liyecom
AI智能 clawhub v0.1.2 1 版本 99884.8 Key: 无需
★ 0
Stars
📥 867
下载
💾 25
安装
1
版本
#latest

概述

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

LevelAuto ActionDescription
---------------------------------
CRITICALQuarantineShell injection, supply-chain attacks
HIGHDisableDangerous patterns, external downloads
MEDIUMWarnRisky but not immediately dangerous
LOW/INFOLogInformational 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.

版本历史

共 1 个版本

  • v0.1.2 当前
    2026-03-29 12:12 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-intelligence

Proactive Agent

halthelobster
将AI智能体从任务执行者升级为主动预判需求、持续优化的智能伙伴。集成WAL协议、工作缓冲区、自主定时任务及实战验证模式。Hal Stack核心组件 🦞
★ 837 📥 213,338
ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,362 📥 318,826
ai-intelligence

Nano Banana Pro

steipete
使用 Nano Banana Pro (Gemini 3 Pro Image) 生成或编辑图像。支持文生图、图生图及 1K/2K/4K 分辨率,适用于图像创建、修改及编辑请求,使用 --input-image 指定输入图像。
★ 418 📥 115,308