📦 免费版 — AI合同风险速览
v1.3.0上传合同即可秒获AI风险分析：高亮条款、通俗解释、谈判要点与缺失保护清单，免费版每日限3份。
0· 158·2 当前·2 累计
by 下载技能包
最后更新
2026/3/29
安全扫描
OpenClaw
安全
high confidenceNULL
评估建议
This skill appears to do what it says (contract scanning) and does not ask for extra credentials or install code. Before using it with sensitive contracts: 1) Verify where your files are sent — check your OpenClaw agent's configured AI provider and its privacy/retention policy; 2) If you must upload sensitive or regulated documents, prefer an on-prem or trusted provider or consult a lawyer instead of relying solely on AI; 3) Be cautious about paid setup offers or contact handles (the SKILL.md re...详细分析 ▾
✓ 用途与能力
Name, description, triggers and SKILL.md all describe clause-by-clause contract review, risk scoring, missing-protection checklist and negotiation suggestions. The skill does not request unrelated binaries, environment variables, or config paths, which is proportionate to its stated purpose.
ℹ 指令范围
Runtime instructions are scoped to ingesting uploaded contract files or pasted text and producing a structured report. The SKILL.md repeatedly asserts that files 'only' flow between local OpenClaw and the user's configured AI, and mentions supported external AI providers (阿里云百炼, DeepSeek) and entering keys in OpenClaw — that data-flow/privacy statement is a claim in prose and not enforced by any install or config in the skill bundle itself, so users should verify where data is actually sent by their OpenClaw agent and the chosen provider.
✓ 安装机制
No install spec or code files are present (instruction-only skill). Nothing is downloaded or written to disk by the skill package itself, which minimizes supply-chain risk.
ℹ 凭证需求
The skill declares no required environment variables or credentials. However, it assumes the user has configured an AI backend (and mentions third-party providers) which may require API keys in the user's OpenClaw environment — those keys are external to the skill and not requested by it. Users should ensure any provider keys they configure have appropriate scope and trust level.
✓ 持久化与权限
always is false and the skill does not request or modify system-level configs. It is user-invocable only, so it will not be force-included in every agent run.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.3.02026/3/28
NULL
● 无害
安装命令
点击复制官方npx clawhub@latest install ai-contract-reviewer
镜像加速npx clawhub@latest install ai-contract-reviewer --registry https://cn.longxiaskill.com