2428424081cn/skill-mcp/adversarial-critic
Claude Code and agent skill by 2428424081cn/skill-mcp
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
红蓝对抗与魔鬼代言人思考工具。扮演挑剔的黑客与架构师,对自身方案进行极限压力测试与漏洞攻击。
Install
npx vskill@latest install 2428424081cn/skill-mcp/adversarial-criticSKILL.md
The same SKILL.md was published earlier as 2428424081cn/skill-mcp/adversarial-critic.
红蓝对抗与魔鬼代言人 (Adversarial Critic)
好方案是打磨出来的,伟大的方案是被攻击出来的。不要急于证明自己是对的,先证明自己无法被击溃。
核心攻击维度
- 时序与并发攻击(Race Conditions):
- 如果两个线程在同一纳秒到达某一行代码,会发生什么?
- 极端边界攻击(Edge Cases):
- 数组长度为 0、值为负数、字符串长度为 100MB、UTF-8 特殊字符?
- 故障注入攻击(Chaos Engineering):
- 依赖的下游服务在第 4.99 秒超时?
- 写入磁盘写到一半时突然断电?
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/reasoning/adversarial-critic/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/2428424081cn/skill-mcp/adversarial-critic)