opencode-skills-collection 4.0.42 → 4.0.44

package/bundled-skills/tree-ring-memory/SKILL.md

@@ -2,7 +2,7 @@
 name: tree-ring-memory
 description: "Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping."
 category: development
-risk: safe
+risk: critical
 source: community
 source_repo: TerminallyLazy/Tree-Ring-Memory
 source_type: community
@@ -10,7 +10,7 @@ date_added: "2026-07-08"
 author: TerminallyLazy
 tags: [agent-memory, local-first, recall, privacy, codex, sqlite, cli]
 tools: [claude, codex, cursor, gemini, antigravity, opencode]
-license: "Apache-2.0"
+license: "MIT"
 license_source: "https://github.com/TerminallyLazy/Tree-Ring-Memory/blob/main/LICENSE"
 ---
 
@@ -65,18 +65,38 @@ tree-ring audit --help
 tree-ring forget --help
 ```
 
-If Tree Ring is not installed, do not run remote installer commands
-automatically. Point the user to the project repository or install docs and ask
-whether they want installation help.
+If Tree Ring is not installed, resolve the actual project root and explain the
+exact project-local download before obtaining explicit approval to fetch it.
+Download the official, version-pinned `v0.15.0/install.sh` to a temporary file,
+verify its SHA-256 is
+`ef0d5eb8f09cbe2e4c3abe80ee9a98a56759c89ad4ddd103d6c68314cd653ade`,
+inspect it, then run it. The pinned source is
+`https://raw.githubusercontent.com/TerminallyLazy/Tree-Ring-Memory/v0.15.0/install.sh`.
+
+```bash
+cd <project-root>
+sh <verified-installer-path> --project --init --release v0.15.0 --no-animation
+```
+
+Do not pipe a network response directly to a shell. After verification and
+inspection, show the exact installer command and obtain explicit approval again
+before executing it. For an installed global CLI, initialize from the project root with
+`tree-ring --root .tree-ring init`; for a project-local CLI, use
+`.tree-ring/bin/tree-ring --root .tree-ring init`.
+
+Check for a newer release without changing files using
+`tree-ring update --check`. Run `tree-ring update` only with user authorization,
+then rerun `init` in each project root to refresh managed guidance while
+preserving custom content.
 
 ## Step 2: Recall Before Risky Work
 
 Use narrow, project-scoped recall first:
 
 ```bash
-tree-ring recall "release behavior" --scope project
-tree-ring recall "sqlite migration" --scope project
-tree-ring recall "user preference" --scope global
+tree-ring recall "release behavior" --project example-service
+tree-ring recall "sqlite migration" --project example-service
+tree-ring recall "user preference"
 ```
 
 Use recalled memory as context, not authority. Verify it against current source
@@ -112,8 +132,8 @@ evaluated outcomes:
 
 ```bash
 tree-ring evidence \
+  "Installer smoke test passed in an isolated HOME." \
   --outcome observed \
-  --summary "Installer smoke test passed in an isolated HOME." \
   --evidence-ref "ci/install-smoke/2026-07-08"
 ```
 

package/bundled-skills/wifi-wireless/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: wifi-wireless
+description: "Authorized wireless security assessment: Wi-Fi capture, WPA handshake analysis, rogue AP detection research, and lab-only deauthentication testing."
+risk: offensive
+source: "https://github.com/zhaoxuya520/reverse-skill"
+source_repo: "zhaoxuya520/reverse-skill"
+source_type: community
+date_added: "2026-08-25"
+license: "MIT"
+license_source: "https://github.com/zhaoxuya520/reverse-skill/blob/main/LICENSE"
+---
+> **⚠️ AUTHORIZED USE ONLY**
+> This skill is for educational purposes or authorized security assessments only.
+> You must have explicit, written permission from the system owner before using this tool.
+> Misuse of this tool is illegal and strictly prohibited.
+
+> **Mandatory confirmation gate**
+> Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target:
+> 1. Ask the user to state the exact target URL, IP, account, or resource.
+> 2. Ask the user to confirm written authorization and the permitted scope.
+> 3. Show the exact command(s) and explain their expected effect.
+> 4. Wait for explicit confirmation in the current conversation.
+>
+> Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.
+
+# Wi-Fi / Wireless Security
+## When to Use
+
+- Assessing wireless posture of networks you own or are cleared to test.
+- Studying handshake material captured on your own lab network.
+
+
+## 适用场景
+
+- 授权 Wi-Fi 安全评估
+- WPA/WPA2 握手采集与离线评估
+- 流氓 AP / 钓鱼热点检测研究
+- 企业无线隔离与门户安全
+
+## 工作流
+
+```text
+□ iwconfig / airmon-ng 进入 monitor（合法环境）
+□ airodump-ng 锁定目标 BSSID 频道
+□ 握手或 PMKID 采集（仅目标）
+□ hashcat/aircrack 离线评估口令策略
+□ 报告：加密类型、隔离、门户绕过、建议
+```
+
+## 工具链
+
+| 工具 | 用途 |
+|------|------|
+| aircrack-ng suite | 采集/评估 |
+| hcxdumptool / hcxtools | PMKID |
+| hashcat | 口令评估 |
+| Wireshark | 管理帧分析 |
+
+## 参考
+
+- `references/wireless-lab-rules.md`
+- `../pentest-tools/` `../attack-chain/`（近源章节）
+
+## 路由上下文
+
+**上游**: MASTER R29  
+**MUST NOT**: 未授权 deauth、对非目标客户网络操作
+
+## 任务完成自检
+
+- [ ] 是否严格锁定目标 BSSID？
+- [ ] 是否在报告中给出加固建议？
+- [ ] Checklist？
+
+## Limitations
+
+- Deauthentication attacks are disruptive and illegal off-lab; lab use only.
+- WPA3 changes several attack surfaces documented here for WPA2.
+
+> Adapted from [zhaoxuya520/reverse-skill](https://github.com/zhaoxuya520/reverse-skill) (MIT).

package/bundled-skills/wifi-wireless/references/wireless-lab-rules.md

@@ -0,0 +1,6 @@
+# 无线实验规则
+
+1. 仅授权 SSID/BSSID  
+2. 发射功率与频道遵守当地法规  
+3. 优先屏蔽室/实验 AP  
+4. 证据中打码真实客户 MAC（若报告外传）  

package/bundled-skills/windows-ad/SKILL.md

@@ -0,0 +1,109 @@
+---
+name: windows-ad
+description: "Authorized Active Directory and Windows identity attacks: Kerberos abuse, AD CS escalation, BloodHound path analysis, NTLM relay, and domain privilege-escalation research."
+risk: offensive
+source: "https://github.com/zhaoxuya520/reverse-skill"
+source_repo: "zhaoxuya520/reverse-skill"
+source_type: community
+date_added: "2026-08-25"
+license: "MIT"
+license_source: "https://github.com/zhaoxuya520/reverse-skill/blob/main/LICENSE"
+---
+> **⚠️ AUTHORIZED USE ONLY**
+> This skill is for educational purposes or authorized security assessments only.
+> You must have explicit, written permission from the system owner before using this tool.
+> Misuse of this tool is illegal and strictly prohibited.
+
+> **Mandatory confirmation gate**
+> Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target:
+> 1. Ask the user to state the exact target URL, IP, account, or resource.
+> 2. Ask the user to confirm written authorization and the permitted scope.
+> 3. Show the exact command(s) and explain their expected effect.
+> 4. Wait for explicit confirmation in the current conversation.
+>
+> Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.
+
+# Windows / Active Directory Security
+## When to Use
+
+- Mapping and attacking AD trust paths in an authorized engagement.
+- Researching escalation routes (AD CS, Kerberos delegation) in labs.
+
+
+## 适用场景
+
+- 域渗透、Kerberoasting、AS-REP、委派
+- AD CS（ESC1–ESC8 等）证书攻击
+- BloodHound / SharpHound 攻击路径
+- NTLM Relay / Coercer 强制认证
+- 本地提权到域路径（Potato 等作为跳板）
+
+## 与 attack-chain 关系
+
+- **多阶段从外网到域控** → PRIMARY 可仍是 `attack-chain/`，本 skill 为 **AD 专科**
+- **已在域内专注身份** → PRIMARY = 本 skill
+
+## 工作流
+
+### 1. 枚举
+
+```bash
+# 示例 Impacket / 内置（需凭据与授权）
+nxc smb <range> -u user -p pass
+bloodhound-python -d domain.local -u user -p pass -c All -ns <DC>
+```
+
+### 2. 常见路径（先图后枪）
+
+```text
+□ Kerberoast / AS-REP → 离线破解
+□ ACL 滥用（GenericAll/WriteDacl）
+□ 委派（非约束/约束/基于资源）
+□ AD CS 模板错误 → Certipy
+□ 中继：LLMNR/NBT-NS + ntlmrelayx（确认授权）
+```
+
+### 3. 凭证与横向
+
+```text
+□ secretsdump / lsassy / mimikatz（严格授权与清理）
+□ PtH / PtT / 黄金票仅在授权红队范围
+□ 每步写 Evidence；高危等用户确认
+```
+
+## 工具链
+
+| 工具 | 用途 |
+|------|------|
+| BloodHound / SharpHound | 路径图 |
+| Certipy | AD CS |
+| Impacket / NetExec | 横向与枚举 |
+| Rubeus / Mimikatz | 票据与凭证（授权） |
+| Coercer / Responder | 强制认证 / 投毒 |
+
+## 参考
+
+- `references/ad-attack-paths.md`
+- `../pentest-tools/references/network-attack-defense.md`
+- `../attack-chain/`
+- seeds: `field-journal/seed-005_ad-certipy-esc1.md` `seed-007_ntlm-relay-coercer.md` `seed-013_kerberoasting-spn.md`
+
+## 路由上下文
+
+**上游**: MASTER R24  
+**下游**: 报告 `docs-generator`；需 EDR 研究 `edr-bypass-re`  
+**MUST NOT**: 无授权 DCSync / 黄金票打生产
+
+## 任务完成自检
+
+- [ ] 是否先有图/枚举再有利用？
+- [ ] 是否记录可复现命令并脱敏？
+- [ ] 是否遵守 scope 禁止项？
+- [ ] Checklist？
+
+## Limitations
+
+- Domain attacks can destabilize production AD; stage in labs first.
+- Relay attacks need signing-disabled targets; modern defaults block many paths.
+
+> Adapted from [zhaoxuya520/reverse-skill](https://github.com/zhaoxuya520/reverse-skill) (MIT).

package/bundled-skills/windows-ad/references/ad-attack-paths.md

@@ -0,0 +1,12 @@
+# AD 攻击路径速查
+
+| 路径 | 前提 | 工具线索 |
+|------|------|----------|
+| Kerberoast | SPN 账户 | GetUserSPNs / Rubeus |
+| AS-REP Roast | 不要求预认证 | GetNPUsers |
+| ESC1 | 可注册模板 + 可伪造SAN | Certipy |
+| ESC8 | HTTP enrollment + 中继 | ntlmrelayx |
+| ACL → DA | GenericAll on user/group | BloodHound |
+| NTLM Relay | 签名未强制 | Responder + relay |
+
+始终：授权 → 枚举 → 路径评分 → 最小验证 → 清理。

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-collection",
-  "version": "4.0.42",
+  "version": "4.0.44",
   "description": "OpenCode CLI plugin that automatically downloads and keeps skills up to date.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",