← Back to Skills Marketplace
506
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install contract-risk-helper
Description
Contract Risk Helper — scan contracts for common risk clauses. Triggers on 合同风险、合同审查、条款风险、帮我看合同、合同检查. Read-only local analysis, no network calls, no credenti...
README (SKILL.md)
Contract Risk Helper
Overview
Contract Risk Helper identifies common risk clauses in contract text using local pattern matching. No network calls, no credential access, no exec — pure read-only text analysis.
⚠️ Disclaimer: Preliminary identification only. Not legal advice. Consult a qualified attorney for important decisions.
When to Use
- User provides contract text and asks for risk scan
- Keywords: 合同风险、合同审查、条款风险、帮我看合同、合同检查、扫描合同
Workflow
- Receive contract text — user provides full contract or specific clauses
- Identify contract type — service agreement, NDA, employment, lease, etc.
- Run local pattern scan — match against known risk patterns (reference file)
- Return findings — categorized by severity (critical/warning/advisory) with suggestions
- Flag for attorney review — for critical items
Risk Categories
| Severity | Examples |
|---|---|
| 🔴 Critical | Unlimited liability, no termination for convenience, broad indemnification |
| 🟡 Warning | Net 60+ payment, auto-renewal without notice, work-for-hire without scope limit |
| 🟢 Advisory | Missing dispute resolution clause, ambiguous definitions |
Output Format
## 风险扫描结果
共发现 N 个风险项
### 🔴 Critical (X)
- **[条款位置]** 描述
→ 建议操作
### 🟡 Warning (X)
- **[条款位置]** 描述
→ 建议操作
Notes
- All analysis is local pattern matching against reference/common-risks.md
- No data leaves the local environment
- Does not store or transmit contract content
- No external API calls
Usage Guidance
This package appears to do exactly what it says: local regex-based identification of common contract risks. Before installing or running, consider: (1) the skill will process whatever contract text you provide — avoid submitting extremely sensitive or regulated data unless you trust the host environment, (2) verify your platform does not inadvertently log or transmit skill inputs (the code itself does not transmit data), and (3) note small non-security oddities (skill.json version differs from registry version and the references file exists but is not programmatically used). If you need legal certainty, use this as a preliminary tool only and consult a qualified attorney.
Capability Analysis
Type: OpenClaw Skill
Name: contract-risk-helper
Version: 1.0.1
The contract-risk-helper skill is a legitimate tool designed for local text analysis. The code in handler.py and scripts/scanner.js uses standard regular expressions to identify specific legal risk patterns (e.g., unlimited liability, auto-renewal) without any network calls, file system access, or shell execution. There are no signs of prompt injection, data exfiltration, or obfuscation across any of the files.
Capability Assessment
Purpose & Capability
Name/description (contract risk scanning) matches the provided code and reference material. The handlers implement pattern matching for common contract clauses and return categorized results; nothing in the package requests unrelated capabilities (no cloud credentials, no unrelated binaries).
Instruction Scope
SKILL.md directs only local pattern matching over user-provided contract text. The runtime code (handler.py and scripts/scanner.js) only reads in text arguments and applies regexes; it does not read system files, environment variables, or contact external endpoints. The SKILL.md claim of 'no network calls, no exec' is consistent with the code (there are shebang lines in scripts but no subprocess or shell.exec usage).
Install Mechanism
No install spec is present (instruction-only from platform perspective) and included code has no external download or package-install behavior. Files are plain source code and tests; nothing is fetched from arbitrary URLs or written to unexpected locations.
Credentials
No required environment variables, credentials, or config paths are declared or used. The skill appropriately requests no secrets given its stated purpose.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide settings. It is user-invocable and can be invoked autonomously per platform defaults, which is expected for this kind of skill.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install contract-risk-helper - After installation, invoke the skill by name or use
/contract-risk-helper - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Initial release. Read-only local pattern scan for contract risk clauses. No exec, no network, no credential access.
v1.0.0
Initial release of the contract-risk-helper skill.
- Introduced an auto-update tool for managing OpenClaw skill updates.
- Provides safe update features: version checking, automatic local backups, and rollback support.
- Includes configuration management (blacklist, auto-upgrade strategies, quiet hours).
- Only reads local files; all actual updates are executed via the clawhub CLI.
- Easy management of backups, cache, and update strategies through simple command-line commands.
Metadata
Frequently Asked Questions
What is Contract Risk Helper?
Contract Risk Helper — scan contracts for common risk clauses. Triggers on 合同风险、合同审查、条款风险、帮我看合同、合同检查. Read-only local analysis, no network calls, no credenti... It is an AI Agent Skill for Claude Code / OpenClaw, with 506 downloads so far.
How do I install Contract Risk Helper?
Run "/install contract-risk-helper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Contract Risk Helper free?
Yes, Contract Risk Helper is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Contract Risk Helper support?
Contract Risk Helper is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Contract Risk Helper?
It is built and maintained by haidong (@harrylabsj); the current version is v1.0.1.
More Skills