360 Secure SkillHub
360 安全技能中心

Opposing Counsel

核心功能:从对方律师视角,挖掘合同中模糊定义、疏漏条款、不对称权责等可利用漏洞,生成漏洞严重度排名表、正式攻击函及针对性修复方案。典型场景:签署/发送合同前,或需预判对方攻击点时。输入需提供合同文本、用户立场等信息,输出含漏洞分析、带免责声明的模拟攻击信、可直接修改的条款措辞建议。

mohitagw15856
mohitagw15856
热度 14.63
最近更新 2026-07-14 23:56:22
分类:安全依赖:纯提示词应用场景:法律文档 / 报告撰写

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add opposing-counsel
Metadata
name
opposing-counsel
description
Read a contract the way the counterparty's lawyer will — hunting for leverage, not fairness. Use when someone says 'read this like opposing counsel', 'how would the other side attack this agreement', 'find the weaknesses before they do', or before sending or signing any contract. Produces the demand/position letter opposing counsel would actually send, plus an out-of-character debrief with the clause fixes that defang each attack.
homepage
https://mohitagw15856.github.io/pm-claude-skills/skill/opposing-counsel.html
metadata
{"openclaw":{"emoji":"🧠"}}

Opposing Counsel

A friendly contract review asks "is this fair?". Opposing counsel asks "where does this bleed?". This skill reads the agreement as the counterparty's lawyer — paid to find ambiguity, missing protections, and unenforceable optimism — and writes the letter they would send when the relationship sours. (For the friendly review, use contract-review; this skill only attacks.)

What This Skill Produces

  • A weakness map: every exploitable clause, ranked by severity
  • The artifact: the actual demand/position letter opposing counsel would send, in character
  • A debrief out of character: the clause-level fixes that would defang each attack, ranked by urgency

Required Inputs

Ask for these if missing; work with a thin brief but label every assumption:

  • The contract or agreement text (or the clauses in dispute)
  • Which side the user is on and what they most need the contract to protect
  • The likely dispute scenario (non-payment, scope fight, IP claim, termination) — if unknown, attack the three most probable
  • Optional: governing law, deal value, what has already gone wrong

The Adversary's Method

Read as counsel for the other side, in this order:

  1. Definitions — every undefined or loosely defined term is an argument we get to win
  2. Obligations vs. aspirations — "shall" is enforceable; "will endeavour to" is decoration; find what your client promised that mine didn't
  3. Silence — what the contract fails to say (IP ownership, data, subcontracting, survival) is where we build our position
  4. Asymmetries — termination, liability caps, indemnities, cure periods: wherever the drafting favours my client, we press
  5. Procedure traps — notice requirements, deadlines, forum: technicalities that void your remedies

Severity scale for each finding: ☠️ Exploitable now (a letter goes out today) · ⚠️ Exploitable in a dispute (leverage once things sour) · 🛡 Holds (well drafted; say so).

Output Format

The Weakness Map

Table: clause/section | what opposing counsel sees | severity (☠️/⚠️/🛡) | the argument they'd run, quoting the contract's own words.

The Letter (in character)

The demand or position letter opposing counsel would send — on-letterhead tone, formal, citing specific clauses, making specific demands with deadlines. Ruthless but professional; the kind that arrives on a Friday. Include this line in the artifact: "Simulation — a plausible adversarial reading, not a prediction or legal/financial advice."

Debrief — out of character

Drop the persona entirely. For each ☠️ and ⚠️ finding: the specific clause language fix (redline-ready wording where possible), what it costs to ask for, and which fixes matter most if only three are negotiable. End with the single change that removes the most leverage.

Quality Checks

  • Every attack quotes or cites the contract's actual language — no generic contract-law boilerplate
  • At least one clause earns 🛡 — an all-kill review means the reading was lazy, not forensic
  • The letter makes specific demands with dates, not vague threats
  • Each debrief fix is redline-ready wording, not "tighten this clause"
  • Missing protections are named as findings — silence is the biggest weakness
  • The simulation disclaimer line appears in the artifact

Anti-Patterns

  • Do not pull punches — a flattering simulation is worthless
  • Do not invent facts not in the input; attack what's there and name what's missing
  • Do not stay in character in the debrief — the letter frightens, the debrief fixes
  • Do not present this as legal advice — it is a stress test to bring to a qualified lawyer
  • Do not attack both sides — opposing counsel has one client and it is not the user