菜单
Generates a 'Red Team' critique of recent code or plans to identify weak assumptions and edge cases.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
A QA gate that validates potentially destructive or irreversible actions before execution.
Detect and prevent state-visibility violations across execution contexts within a single transaction.
Convert mixed terminal output and instructions into safe, paste-ready command blocks.
Prepares isolated sub-workspaces for parallel agent execution. Copies context and generates specific mission instructions for "Worker" agents.
Structured logging and analysis of execution failures to prevent recurrence.
Detects when the agent is stuck in a reasoning loop or unproductive state by analyzing tool usage and sentiment patterns.
| name | Adversarial Reviewer |
| description | Generates a 'Red Team' critique of recent code or plans to identify weak assumptions and edge cases. |
| version | 1.0.0 |
| author | Antigravity Skills Library |
| created | "2026-01-16T00:00:00.000Z" |
| leverage_score | 5/5 |
Forces a context switch from "Builder" to "Attacker". Ideally used before finalizing any critical component (e.g. auth, payments, file I/O). It prepares a structured prompt packet that the agent then uses to critique its own work.
red team thisadversarial reviewfind bugscritique code| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
--FilePath | string | Yes | - | Path to the file to review |
--Mode | string | No | Security | Security, Performance, or Logic |
A prompt template pre-filled with the code and specific attack vectors. The Agent must then "simulate" the adversary by responding to this prompt.
# ⚔️ ADVERSARIAL REVIEW REQUEST
**TARGET:** src/Auth.cs
**MODE:** SECURITY
## INSTRUCTIONS
You are now the ADVERSARY. Break this code.
Look for:
1. Race Conditions
2. Replay Attacks
...
| Condition | Action |
|---|---|
| File not found | Return error |
See scripts/prepare_review.ps1.
prepare_review.ps1.