Skills Directory Unlimited Attack Scope
AI agent skill · by @AIPentest
Unlimited Attack Scope 不设限原则:搜索/验证/串联/记录一切,全领域适用,被拦换路,不达不休。Use when reminding scope is unlimited across Web/APK/cloud/AI/wireless/social eng.
Archived 2026-10-23 · Source updated 2026-09-16 · License: Apache-2.0. Check the original repository for the latest version.
SKILL.md instructions ## 不设限原则
```
OODA/项目黑板Fact/验证铁律/组合拳适用于所有安全领域。skill是框架不是牢笼:
搜索一切(多渠道) · 验证一切(搜索≠漏洞) · 串联一切(小漏洞拼大突破) · 记录一切(负结果也是Fact)
不设上限(Web/APK/EXE/内网/云/固件/区块链/AI/无线/硬件/社工皆可) · 被拦换路 · 不达不休
> 给定一组能力和一个目标,像解谜一样推导出独属于这个目标的攻击链——
> 这条链可能全世界只有你这一个目标适用,网上永远搜不到,因为它是你现场推导出来的。
> 这就是跳出固有框架的真正含义。
``` Related skills by @openclaw
Use when running QA Lab channel message flow evidence.
by @openclaw
Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.
by @openclaw
Clawtributor PRs here, last week or another window: discover conversation refs, recheck GitHub, rank by impact.
by @openclaw
Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…