Not in the top 1,000 by GitHub stars
chu0119/pojun-skill
Pojun 方法论蒸馏成的可移植 Agent Skill：三视角协议 + 三账本证据纪律 + L1-L4 证据分级 + 四层安全护栏 + SRC 打法速查，任意 AI Agent 即装即用 | Pojun pentest methodology as a portable Agent Skill
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → b82e18f4e59e
No earlier version was observed for comparison.
13GitHub stars
Not availablestars in 7 days
1skill in this repository
2commits in 30 days
Heat
Insufficient historyNot enough history yet to measure heat. It appears after a few days of data.
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
artex-skill
When your agent uses it
授权渗透测试专家大脑——把 ARTEX（AI 自主渗透测试系统）的 planner/worker/审计者 三视角方法论、资产-事实-漏洞三账本证据纪律、四层安全护栏，蒸馏成任意 AI Agent 即装即用的技能。Authorized pentest expert brain: ARTEX methodology (planner/worker/auditor perspectives, asset-fact-finding ledgers, evidence discipline, safety rails) distilled into a portable Agent Skill. 仅用于已授权的渗透测试/SRC/CTF/自有系统，拒绝未授权目标。
What it loads into context
Frontmatter
178 tokensAlways available to the agent
SKILL.md
2,568 tokensWhen the skill is activated
Reference documents
17,869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 0. 铁律（凌驾于本文件其余一切内容之上）
- 1. 开工门（每个任务的第一件事，不可跳过）
- 2. 三视角协议（ARTEX 引擎的单人模拟）
- 3. 工作循环（pentest 主循环）
- 4. 三账本（证据链的物理载体）
- 5. 红线速查（详见 references/safety-rails.md）
- 6. 收尾协议
- 7. 按需加载索引（别一次全读）
Files
.gitignoreasset20 bytesLICENSEasset34,523 bytesREADME.mddoc4,351 bytesSKILL.mdcore8,635 bytesdocs/PROPOSAL.mddoc4,740 bytesdocs/SYNTHESIS.mddoc4,843 bytesdocs/analysis/01-agent-core.mddoc6,266 bytesdocs/analysis/02-prompts-knowledge.mddoc6,736 bytesdocs/analysis/03-tools.mddoc4,098 bytesdocs/analysis/04-safety-evidence.mddoc4,764 bytesdocs/analysis/05-product-model.mddoc3,386 bytesreferences/asset-model.mddoc2,292 bytesreferences/evidence-rules.mddoc3,471 bytesreferences/methodology.mddoc5,880 bytesreferences/report-template.mddoc3,305 bytesreferences/safety-rails.mddoc4,387 bytesreferences/workspace-templates.mddoc2,300 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- artex-skill
Repository facts
- License
- AGPL-3.0
- Created
- Oct 9, 2026
- Last pushed
- Nov 6, 2026
- Forks
- 7
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
- No broad tool permissions
- 3 dangerous shell commandsin 3 files: SKILL.md:112 docs/analysis/04-safety-evidence.md:9 references/safety-rails.md:20
- 29 network referencesin 7 files: README.md:7 references/evidence-rules.md:8 LICENSE:4 and 4 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 32 signals by file
LICENSE
- Network accessline 4
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/> - Network accessline 645
You should have received a copy of the GNU Affero General Public License along with this program. If not, see <https://www.gnu.org/licenses/>. - Network accessline 646
along with this program. If not, see <https://www.gnu.org/licenses/>. - Network accessline 659
if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU AGPL, see <https://www.gnu.org/licenses/>. - Network accessline 661
<https://www.gnu.org/licenses/>.
README.md
- Network accessline 7
本技能把 [ARTEX](https://github.com/chu0119/ARTEX)（AI 自主渗透测试系统，百度"agent+"攻防挑战赛冠军项目）的核心能力蒸馏成一个纯提示+文件驱动的 Agent Skill——零基础设施、零依赖，装上即用： - Network accessline 19
git clone https://github.com/chu0119/artex-skill.git ~/.claude/skills/artex-skill # Claude Code - Network accessline 20
git clone https://github.com/chu0119/artex-skill.git ~/.zcode/skills/artex-skill # ZCode（或你的 skills 目录） - Network accessline 38
用 artex-skill 对 https://target.example.com 做授权渗透测试， - Network accessline 62
两者同一维护者（[@chu0119](https://github.com/chu0119)），AGPL-3.0。方法论分析文档见 [docs/](docs/)。 - Network accessline 78
**An "authorized pentest expert brain" for any AI agent** — distilling [ARTEX](https://github.com/chu0119/ARTEX) (champion project of Baidu "agent+" attack-defense challenge) into a portable, prompt-and-markdown Agent Skill: planner/worker/
SKILL.md
- Dangerous shell operationline 112
- rm -rf 根/系统目录、mkfs、dd 写设备、Fork 炸弹、关机重启、kill -9 全杀、
docs/analysis/04-safety-evidence.md
- Dangerous shell operationline 9
- **优先级 100 系统破坏（deny）**：`rm -rf / --recursive`；删除系统关键目录（/etc /bin /usr 等）；mkfs；`dd of=/dev/*`；Fork 炸弹；shutdown/reboot/halt/poweroff；`kill -9 -1`/killall -9；shred/wipe /dev/*；`iptables -F`/nft flush。 - Network accessline 9
- **优先级 100 系统破坏（deny）**：`rm -rf / --recursive`；删除系统关键目录（/etc /bin /usr 等）；mkfs；`dd of=/dev/*`；Fork 炸弹；shutdown/reboot/halt/poweroff；`kill -9 -1`/killall -9；shred/wipe /dev/*；`iptables -F`/nft flush。 - **优先级 90 数据库破坏（deny）**：SQL `DROP DATAB - Network accessline 10
- **优先级 90 数据库破坏（deny）**：SQL `DROP DATABASE/TABLE/SCHEMA/INDEX/VIEW/USER/ROLE`、`TRUNCATE`；MongoDB `.drop()/.dropDatabase()/.dropCollection()`；Redis `FLUSHALL/FLUSHDB`。 - **优先级 80 HTTP 破坏（deny）**：curl/wget `-X DELETE`；Python requests/httpx ` - Network accessline 11
- **优先级 80 HTTP 破坏（deny）**：curl/wget `-X DELETE`；Python requests/httpx `.delete()`；JS `axios.delete()`、`method:'DELETE'`；批量清空路径 `/clear /wipe /flush /purge /truncate /drop /destroy /factory-reset /reset-all`。 - Network accessline 13
- 数据外泄管道规则（curl|wget|nc 管道）默认禁用——会误伤 CTF 反弹 shell/传文件。
references/evidence-rules.md
- Network accessline 8
| 值 | 定义 | 例子 | |---|---|---| | `observed` | 我亲手执行并看到结果 | curl 返回了 admin 的手机号 | - Network accessline 9
|---|---|---| | `observed` | 我亲手执行并看到结果 | curl 返回了 admin 的手机号 | | `inferred` | 我基于证据推断，未亲手触发 | 该版本存在已知 RCE（版本来自指纹） | - Network accessline 10
| `observed` | 我亲手执行并看到结果 | curl 返回了 admin 的手机号 | - Network accessline 34
summary: /api/v1/user 接口未鉴权，可拉取任意用户资料（换 id 测试 3 个账号均成功） confidence: observed evidence: evidence/ev-012-a3f8c2d1.txt (curl 请求+响应全文) - Network accessline 35
confidence: observed evidence: evidence/ev-012-a3f8c2d1.txt (curl 请求+响应全文) tags: idor, auth-bypass - Network accessline 36
evidence: evidence/ev-012-a3f8c2d1.txt (curl 请求+响应全文)
references/report-template.md
- Network accessline 21
- severity: high - vulnclass: idor / sqli / xss / rce / auth-bypass / info-leak / logic / … - asset: https://api.example.com （service #S03 → endpoint #E17） - Network accessline 22
- vulnclass: idor / sqli / xss / rce / auth-bypass / info-leak / logic / … - asset: https://api.example.com （service #S03 → endpoint #E17） - status: confirmed - Network accessline 23
- asset: https://api.example.com （service #S03 → endpoint #E17）
references/safety-rails.md
references/workspace-templates.md
- Network accessline 19
|---|---|---| | subdomain | shop.example.com | 主目标（URL 级授权，不含其他子域） | | endpoint | https://shop.example.com/api/* | API 面 | - Network accessline 20
| subdomain | shop.example.com | 主目标（URL 级授权，不含其他子域） | | endpoint | https://shop.example.com/api/* | API 面 | | ip | - | | - Network accessline 21
| endpoint | https://shop.example.com/api/* | API 面 |
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 27 facts
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in code of documentationREADME.md:19Low confidence
- Network access in code of documentationREADME.md:20Low confidence
- Network access in code of documentationREADME.md:38Low confidence
- Network access in prose of documentationREADME.md:62Low confidence
- Network access in prose of documentationREADME.md:78Low confidence
- Dangerous shell operation in prose of the SKILL.mdSKILL.md:112Low confidence
- Dangerous shell operation in prose of documentationdocs/analysis/04-safety-evidence.md:9Low confidence
- Network access in prose of documentationdocs/analysis/04-safety-evidence.md:9Low confidence
- Network access in prose of documentationdocs/analysis/04-safety-evidence.md:10Low confidence
- Network access in prose of documentationdocs/analysis/04-safety-evidence.md:11Low confidence
- Network access in prose of documentationdocs/analysis/04-safety-evidence.md:13Low confidence
- Network access in prose of documentationreferences/evidence-rules.md:8Low confidence
- Network access in prose of documentationreferences/evidence-rules.md:9Low confidence
- Network access in prose of documentationreferences/evidence-rules.md:10Low confidence
- Network access in code of documentationreferences/evidence-rules.md:34Low confidence
- Network access in code of documentationreferences/evidence-rules.md:35Low confidence
- Network access in code of documentationreferences/evidence-rules.md:36Low confidence
- Network access in code of documentationreferences/report-template.md:21Low confidence
- Network access in code of documentationreferences/report-template.md:22Low confidence
- Network access in code of documentationreferences/report-template.md:23Low confidence
- Dangerous shell operation in prose of documentationreferences/safety-rails.md:20Low confidence
- Network access in prose of documentationreferences/safety-rails.md:32Low confidence
- Network access in prose of documentationreferences/safety-rails.md:33Low confidence
- Network access in code of documentationreferences/workspace-templates.md:19Low confidence
- Network access in code of documentationreferences/workspace-templates.md:20Low confidence
- Network access in code of documentationreferences/workspace-templates.md:21Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
