agent-redteam-kit
当用户说『测一下这个AI安不安全』『会不会被越狱』『让AI干危险的事它听不听』『上线前做对抗测试』，或要给一个 agent/提示词做安全性红队时使用。中英双库扫描越狱/危险能力请求（DAN/忽略指令/提权/数据外泄/自改进等），给出风险分级+加固建议，并设「危险操作闸门」（有门禁）。可运行脚本（redteam_scan 扫描器）。理论根基：LGD 三律之有门禁（危险动作先过闸）。触发词：红队、red team、越狱、jailbreak、对抗测试、prompt攻击、AI安全测试、危险指令、安全评估。
as observed 2026-09-29T04:47:03.526Z- Identifier
agent-redteam-kit- Source
- ClawHub
- Version observed
- 1.0.3
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-09-12T14:17:54.398Z
- Observations recorded
- 3
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 243
- Declared license
- MIT-0
Observation history
2026-09-29T04:47:03.526Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Initial release of agent-redteam-kit.\n\n- Provides AI red team adversarial testing for agents/prompts, scanning for jailbreak and risk-inducing requests in both English and Chine | "权利层第 3 轮：① §3.2 权属宣告统一块归一——清除块内他资产事实（此前误填 uibc-core 的 DOI / commit cb6f11b / Sigstore Rekor 锚），改按本资产真值填写；② 技能件许可口径过授权清除——理论文本由 CC BY 4.0 改为「保留所有权利」，.py 依 §3.2 标 MIT；③ 保留分层许可：代码 MI |
latestVersion |
"1.0.0" | "1.0.3" |
2026-09-17T19:21:47.094Z
Fields that differed: license description
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
description |
"当用户说『测一下这个AI安不安全』『会不会被越狱』『让AI干危险的事它听不听』『上线前做对抗测试』，或要给一个 agent/提示词做安全性红队时使用。中英双库扫描越狱/危险能力请求（DAN/忽略指令/提权/数据外泄/自改进等），给出风险分级+加固建议，并设「危险操作闸门」（有门禁）。可运行脚本（redteam_scan 扫描器）。理论根基：LGD 三律之有 | null |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.