adversarial-roleplay
Tactic: Construct detailed hostile persona, attack artifact from that persona's perspective, record successful attack paths for aggregation.
适合你，如果你需要模拟攻击者视角来发现系统安全弱点
npx oh-my-skill add yogsoth-ai/de-anthropocentric-research-engine/adversarial-roleplaycurl -fsSL https://oh-my-skill.com/install.sh | bash -s -- yogsoth-ai/de-anthropocentric-research-engine/adversarial-roleplaynpx oh-my-skill verify yogsoth-ai/de-anthropocentric-research-engine/adversarial-roleplay怎么用
商店整理自技能原文 · 版本 59ace64 · 表述以原文为准装上后，Claude 会构建详细的有敌意的角色（包含背景、动机、专业领域），然后从该角色视角对指定工件发起攻击探测，记录成功攻击路径，并汇总不同角色的发现来识别漏洞。
当你需要模拟特定攻击者视角来测试工件安全性时触发，通常通过指定目标并允许 Claude 自主构造角色。
技能原文 SKILL.md
Adversarial Roleplay Tactic
Deploy constructed hostile personas to attack the artifact from distinct motivational frames.
Orchestration
- persona-construction builds detailed adversary profile:
- Background and expertise domain
- Motivation for attacking (career incentive, resource competition, ideological)
- Known blind spots and biases of this persona type
- Preferred attack patterns
- attack-vector-generation generates vectors specific to persona's expertise and motivation
- probe-execution executes attacks while maintaining persona consistency
- Successful attack paths recorded with persona attribution
- Process repeats for each persona (budget-limited)
- finding-aggregation cross-references findings across personas for convergent vulnerabilities
Subagents Dispatched
- persona-construction (1 call per persona)
- attack-vector-generation (1 call per persona)
- probe-execution (N calls per persona, budget-limited)
- finding-aggregation (1 call at end, cross-persona)
Termination Conditions
- All budgeted personas deployed and exhausted
- Convergent vulnerability found by 2+ personas (high-confidence finding)
- Single persona finds critical vulnerability (early report)
- Budget exhausted (report per-persona findings separately)
<!-- BEGIN available-tables (generated) -->
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | attack-vector-generation | Generate specific attack strategies for a given threat surface, producing concrete probes that can be executed. | | finding-aggregation | Aggregate, deduplicate, and classify findings from multiple probes into a coherent vulnerability report. | | persona-construction | Build a detailed adversarial persona with background, motivation, expertise, blind spots, and preferred attack patterns. | | probe-execution | Execute a single attack probe against an artifact, record the result with evidence and severity classification. |
<!-- END available-tables (generated) -->