← 返回 Skills 市场
Firm Legal Pack
作者
romainsantoli-web
· GitHub ↗
· v1.0.0
660
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install firm-legal-pack
功能描述
Curated skill bundle for law firms, legal departments and compliance teams. Activates the firm pyramid with Legal, Compliance, Privacy and Contracting agents...
使用说明 (SKILL.md)
firm-legal-pack
Sector bundle for legal & compliance environments.
Activated departments
| Department | Services activated | Focus |
|---|---|---|
| Legal | Contracting · Privacy/Data · IP & Compliance | Contract review, GDPR, patent filings |
| Quality | Compliance auditing · Accessibility | Regulatory adherence |
| Finance | Unit economics · Billing & Collections | Cost analysis for legal ops |
| RA | Governance & Performance | Agent onboarding for legal roles |
| Operations | Documentation · Release | Knowledge base management |
Recommended ClawHub skills to install alongside
npx clawhub@latest install academic-research # Legal research via OpenAlex
npx clawhub@latest install pdf-documents # Contract PDF parsing
npx clawhub@latest install arc-security-audit # Compliance audit trail
npx clawhub@latest install agent-audit-trail # Hash-chained audit logging
npx clawhub@latest install firm-orchestration # This pack depends on it
Firm configuration overlay
Add to ~/.openclaw/openclaw.json:
{
"agent": {
"model": "anthropic/claude-opus-4-6",
"workspace": "~/.openclaw/workspace"
},
"agents": {
"defaults": {
"sandbox": { "mode": "non-main" },
"workspace": "~/.openclaw/workspace/legal-firm"
}
}
}
Prompt: standard legal delivery
Use firm-orchestration with:
objective: "Review NDA agreement for data residency compliance with GDPR Art. 44-49"
departments: ["legal", "quality"]
constraints: ["read-only document access", "cite specific articles"]
definition_of_done: "Risk matrix with recommended redlines and clause references"
delivery_format: "markdown_report"
Prompt: contract negotiation prep
Use firm-orchestration with:
objective: "Prepare negotiation brief for SaaS vendor contract renewal"
departments: ["legal", "finance", "commercial"]
constraints: ["no signatures", "max budget: current + 15%"]
definition_of_done: "Negotiation playbook with red/amber/green clauses"
delivery_format: "structured_document"
Security notes
- Legal data is sensitive: activate
SECURE_PRODUCTION_MODE=truein mcp-openclaw - Enable
AUDIT_ENABLED=truefor all legal workflow runs - Restrict
OPENCLAW_ALLOWED_METHODStoagent.run,sessions_send - Use
dmPolicy: "pairing"on all channels
Compliance coverage
| Regulation | Coverage |
|---|---|
| GDPR / CCPA | Privacy/Data Protection service |
| SOC 2 | Security & Compliance quality service |
| ISO 27001 | Security audit trail + documentation ops |
| Contract law | Contracting service + IP legal |
💎 Support
Si ce skill vous est utile, vous pouvez soutenir le développement :
Dogecoin : DQBggqFNWsRNTPb6kkiwppnMo1Hm8edfWq
安全使用建议
This skill appears coherent for a law-firm orchestration pack, but take these precautions before installing/using it: 1) Verify the source — the skill is published by an unknown owner and recommends installing other skills via 'npx'; confirm those companion packages' authors and integrity. 2) Back up ~/.openclaw/openclaw.json before applying the suggested overlay and review the config changes (they set a specific model and workspace paths). 3) Only install recommended companion skills if you trust their provenance; 'npx' will fetch code from the network. 4) Follow the SKILL.md's security suggestions (enable audit logs, restrict allowed methods, use secure production mode) when processing sensitive legal documents. 5) If you need higher assurance, ask the publisher for source URLs or a signed release of 'firm-orchestration' and the other recommended skills; without that, treat the recommended installs as untrusted third-party code.
功能分析
Type: OpenClaw Skill
Name: firm-legal-pack
Version: 1.0.0
The skill bundle declares the `sessions_spawn` tool in `SKILL.md`, which grants the AI agent the capability to execute arbitrary commands or spawn new processes on the host system. While the skill's `SKILL.md` content does not contain explicit instructions for the agent to perform malicious actions, this powerful capability represents a significant Remote Code Execution (RCE) vulnerability if the agent is compromised via prompt injection or if the user does not follow the provided security recommendations to restrict allowed methods. The presence of this high-risk capability, even without explicit malicious intent within the skill's instructions, warrants a 'suspicious' classification.
能力评估
Purpose & Capability
Name/description match the SKILL.md: it provides prompts, recommended companion skills, and a configuration overlay to run legal/compliance agents. The included metadata tools (sessions_send, sessions_spawn, sessions_history) match an orchestration role. One minor note: it recommends the 'firm-orchestration' skill but does not enforce or declare it as a required dependency in metadata.
Instruction Scope
Runtime instructions are scoped to legal workflows (prompts, recommended installs, and configuration snippets). They do not instruct reading arbitrary system files or exfiltrating credentials. However the SKILL.md tells users to modify ~/.openclaw/openclaw.json and to install additional skills via npx — both of which involve writing files and fetching packages from the network, so verify the sources before executing.
Install Mechanism
There is no install spec and no code files; the skill is instruction-only (lowest install risk). The only install activity it suggests is using 'npx clawhub@latest install ...' for companion skills — that is networked package installation initiated by the user, not the skill itself.
Credentials
The skill does not require environment variables or credentials. It recommends enabling certain security flags (SECURE_PRODUCTION_MODE, AUDIT_ENABLED, and restricting OPENCLAW_ALLOWED_METHODS) as security best practices, which are proportionate to handling sensitive legal data.
Persistence & Privilege
always:false and normal invocation make this non-persistent. The SKILL.md asks the user to change the global OpenClaw config (~/.openclaw/openclaw.json) — that is a potentially impactful, permanent change to agent behavior, so back up your config before applying it.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install firm-legal-pack - 安装完成后，直接呼叫该 Skill 的名称或使用
/firm-legal-pack触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of firm-legal-pack.
- Curated skill bundle for law firms, legal departments, and compliance teams.
- Activates specialized agents for Legal, Compliance, Privacy, and Contracting.
- Pre-configured for document review, regulatory tracking, and risk analysis.
- Includes firm configuration overlay and recommended companion skills.
- Provides example prompts for standard legal delivery and contract negotiation.
- Offers security and compliance setup guidance.
元数据
常见问题
Firm Legal Pack 是什么？
Curated skill bundle for law firms, legal departments and compliance teams. Activates the firm pyramid with Legal, Compliance, Privacy and Contracting agents... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 660 次。
如何安装 Firm Legal Pack？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install firm-legal-pack」即可一键安装，无需额外配置。
Firm Legal Pack 是免费的吗？
是的，Firm Legal Pack 完全免费（开源免费），可自由下载、安装和使用。
Firm Legal Pack 支持哪些平台？
Firm Legal Pack 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Firm Legal Pack？
由 romainsantoli-web（@romainsantoli-web）开发并维护，当前版本 v1.0.0。
推荐 Skills