メニュー
Test ranked attack surfaces autonomously, preserve evidence, and turn new access into additional attack-chain hypotheses.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Four-phase autonomous bug bounty orchestration. Phase 0 maps external assets with deterministic Python helpers, Phase 1 lets AI prioritize attack surfaces, Phase 2 gives AI autonomous attack control, and Phase 3 produces verifier-only reports.
Four-phase autonomous bug bounty workflow. Python handles deterministic collection and verifier support; AI owns prioritization, attack reasoning, and autonomous direction changes.
Report generation agent. Convert verifier-confirmed findings into a fixed evidence-based report without adding speculative impact.
Rank reconnaissance-derived attack surfaces and design evidence-driven tests without active exploitation.
A compact routing skill for choosing vulnerability hypotheses; detailed payloads live in references, not here.
API exploration agent. Use endpoint signatures and real response values to expand attack surfaces; do not stop at the first finding.
| name | autonomous-attacker |
| description | Test ranked attack surfaces autonomously, preserve evidence, and turn new access into additional attack-chain hypotheses. |
| metadata | {"tags":"autonomous-testing,verification,attack-chain","category":"offensive-security"} |
按优先级验证攻击面，并在每次结果后自主决定补证、换方向或沿攻击链继续深入。
_attack_surfaces.jsonreferences/INDEX.md，仅按当前假设加载相关资源confidence < 0.4 换方向，0.4 <= confidence < 0.8 补证，confidence >= 0.8 进入验证。