TheBotique

Gate Policy Generator(权限门禁策略生成器)

Generate a policy-as-code permission file that splits an agent's tools into allowed, needs-review and blocked tiers, with four gates covering overreach, accidental deletion or sending, and runaway loops. 生成 LGD-III 有门禁权限策略

as observed 2026-11-06T15:44:01.797Z
Identifier
gate-policy-generator
Source
ClawHub
Version observed
1.0.11
Source repository
not published
Repository observation
No source repository listed
First observed here
2026-09-12T14:17:54.398Z
Observations recorded
5
Installs (reported upstream)
1
Weekly downloads (upstream)
596
Declared license
MIT-0

Observation history

2026-11-06T15:44:01.797Z

Fields that differed: changelog displayName latestVersion summary

FieldBeforeAfter
changelog "- Major update: multiple files added and removed; documentation overhauled for clarity and accuracy.\n- SKILL.md rewritten in bilingual (EN+ZH), with concise descriptions and clar "安全面加固:permissions 声明改为与包内脚本实际能力一致;新增「数据处理边界」段,明确默认不外发、需人指定目的地并逐次确认。业务逻辑未改动。"
displayName "gate-policy-generator" "Gate Policy Generator(权限门禁策略生成器)"
latestVersion "1.0.4" "1.0.11"
summary "生成 LGD-III「有门禁」权限策略(policy-as-code),给 agent 划清可调用/需评审/禁止的工具边界与四道门禁,防越权、误删误发、失控循环。 适用场景:当需要权限有门禁生成器能力时使用本技能;触发词:gate-policy-generator。" "Generate a policy-as-code permission file that splits an agent's tools into allowed, needs-review and blocked tiers, with four gates covering overreach, accidental deletion or sen
2026-10-17T20:48:50.018Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "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 "- Major update: multiple files added and removed; documentation overhauled for clarity and accuracy.\n- SKILL.md rewritten in bilingual (EN+ZH), with concise descriptions and clar
latestVersion "1.0.3" "1.0.4"
summary "生成 LGD-III「有门禁」权限策略(policy-as-code),给 agent 划清可调用/需评审/禁止的工具边界与四道门禁,防越权、误删误发、失控循环。" "生成 LGD-III「有门禁」权限策略(policy-as-code),给 agent 划清可调用/需评审/禁止的工具边界与四道门禁,防越权、误删误发、失控循环。 适用场景:当需要权限有门禁生成器能力时使用本技能;触发词:gate-policy-generator。"
2026-09-29T04:47:03.526Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "Gate Policy Generator v1.1.0 introduces refined policy generation for AI agent permission boundaries.\n\n- Provides structured LGD-III \"gated permission\" policy outputs to preve "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

FieldBeforeAfter
license null "MIT-0"
description "生成 LGD-III「有门禁」权限策略(policy-as-code),给 agent 划清可调用/需评审/禁止的工具边界与四道门禁,防越权、误删误发、失控循环。" 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.