‹ 首页

adversarial-escalation

@yogsoth-ai · 收录于 5 天前 · 上游提交 2 周前

Strategy: Progressive pressure escalation — starts with surface-level challenges and escalates to fundamental assumption attacks based on defender confidence decay.

适合你,如果需要在安全评估中模拟真实攻击者的逐步升级策略

/ 通过 npx 安装 校验哈希
npx oh-my-skill add yogsoth-ai/de-anthropocentric-research-engine/adversarial-escalation
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- yogsoth-ai/de-anthropocentric-research-engine/adversarial-escalation
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify yogsoth-ai/de-anthropocentric-research-engine/adversarial-escalation
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
388GitHub stars
~520上下文体积 · 单文件
索引托管

怎么用

商店整理自技能原文 · 版本 59ace64 · 表述以原文为准
它做什么

Claude会作为辩论架构师,设计从表面到根本的三层攻击阶梯,并依次用批评者角色挑战你的观点。每一轮攻击后评估你的防御韧性,只有通过才会升级到更深的攻击层次,最终生成辩论总结和裁决。

什么时候触发

当你要求测试某个观点、进行压力辩论,或需要分析论证的薄弱环节时触发。也可在对话中自然启动,如果你提出的主张被Claude认为值得挑战。

装好后可以这样说
触发三层压力测试
Claude会从表面到根本逐步攻击
各层次攻击后给出韧性评分
技能原文 SKILL.md作者撰写 · Apache-2.0 · 59ace64

Adversarial Escalation Strategy

Progressive pressure: escalate attack sophistication based on defender performance.

Method
  1. debate-architect designs escalation ladder (surface → structural → foundational)
  2. Level 1: debate-critic probes surface claims and evidence quality
  3. confidence-calibration measures defender resilience
  4. Level 2: debate-critic attacks structural coherence and logical dependencies
  5. Level 3: debate-critic challenges foundational assumptions and paradigm fit
  6. Each level only reached if defender survives previous level
Budget Table

| Parameter | S | M | L | |---|---|---|---| | Debate rounds | 4 | 8 | 12 | | Participating agents | 3 | 5 | 8 | | Coverage dimensions | 3 | 5 | 7 | | External evidence searches | 2 | 5 | 10 |

Orchestration
debate-architect → [design escalation ladder]
→ [for each level]:
    debate-critic (level-appropriate attack)
    → debate-defender → debate-judge
    → confidence-calibration
    → (escalate if survived, terminate if collapsed)
→ debate-transcript-analysis → verdict-synthesis
Subagents
  • debate-architect (escalation design)
  • debate-critic (multi-level attacks)
  • debate-defender (responses)
  • debate-judge (level adjudication)
  • confidence-calibration (escalation trigger)

<!-- BEGIN available-tables (generated) -->

Available Tactics

Optional, no fixed order; the final leaf is always a sop.

| Tactic | When to use | | --- | --- | | stress-test-dialectical-escalation | Tactic: Progressive debate escalation based on confidence thresholds. Each round increases attack sophistication until defender collapses or proves resilient. |

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use | | --- | --- | | confidence-calibration | Calibrates confidence scores based on debate progression. Determines whether to escalate, continue, or terminate based on cumulative evidence. | | debate-architect | Designs debate structure based on artifact type — selects attack vectors, assigns perspectives, determines escalation ladder, and configures round parameters. | | debate-critic | Generates structured criticism from attack stance using Toulmin model. Produces claims, grounds, warrants, and rebuttals targeting artifact weaknesses. | | debate-defender | Responds to attacks with counter-evidence and counter-arguments. Defends artifact using evidence, clarification, and rebuttal while acknowledging valid criticisms. | | debate-judge | Evaluates debate exchanges, adjudicates argument quality, and produces round verdicts with confidence scores and reasoning. |

<!-- END available-tables (generated) -->

按 Apache-2.0 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。