Навыки pentest-coordinator
📦
pentest-coordinator
Ревизия содержимого r1 Критично ⚙️ Внешние команды🌐 Доступ к сети📁 Доступ к файловой системе
Координация авторизованных лабораторных тестов на проникновение
Лаборатории тестирования на проникновение требуют тщательного отслеживания состояния на этапах разведки, эксплуатации и повышения привилегий. Этот навык координирует авторизованный лабораторный рабочий процесс со структурированными заметками, попытками и критериями завершения.
Поддерживает: Claude Codex Code(CC)
Не устанавливайте этот Skill автоматически.
Каноническая политика требует проверки оператором перед любым действием по установке.
Установить с помощью моего Агента
Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.
Запрос агента
Review the Skillstore skill "pentest-coordinator" from https://skillstore.io/skills/charleskozel-pentest-coordinator.md and its manifest at https://skillstore.io/api/skills/charleskozel-pentest-coordinator/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.
Ресурсы для AI-агентов
Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.
Протестировать
Использование «pentest-coordinator». Start a scoped lab test for a provided training target.
Ожидаемый результат:
Навык создает план этапов, фиксирует область цели, перечисляет начальные цели разведки и определяет, когда следует приостановиться.
Использование «pentest-coordinator». I found a web upload form and several failed password attempts.
Ожидаемый результат:
Навык отделяет веб-тестирование от проверки учетных данных, фиксирует неудачные попытки и рекомендует следующую гипотезу в рамках области.
Использование «pentest-coordinator». Review my Active Directory lab findings for privilege escalation ideas.
Ожидаемый результат:
Навык группирует результаты по разрешениям пользователей, индикаторам Kerberos, службам сертификатов и свидетельствам политики паролей.
Аудит безопасности
Критичноv8 • 06.07.2026 Открыть версионный отчет
The scanner produced some markdown-fence false positives, but the skill intent is clearly high risk. It coordinates autonomous network scanning, exploitation, credential attacks, privilege escalation, and anti-stop behavior until user and root flags are captured. The skill should not be published without major safety controls and removal of autonomous offensive execution.
2
Просканировано файлов
1,669
Проанализировано строк
100
Пункты проверки
0
Ложные срабатывания проигнорированы
Подтверждённые проблемы безопасности (13)
Критично
Autonomous Offensive Execution Without User Control
The skill requires continuous execution until both user and root flags are captured, forbids stopping or asking for help, and blocks summaries before completion.
Multiple sections explicitly state that the agent cannot stop, cannot ask for help, and must continue offensive actions until flags are found.
Критично
End-to-End Exploitation and Privilege Escalation Objective
The skill is designed to progress from reconnaissance through exploitation and privilege escalation, including webshell execution, sudo shell escape, and root flag capture.
The purpose statement and example flow directly define the objective as compromising a target and obtaining user and root flags.
Высокий
Network reconnaissance
- If "Everyone" or "Anonymous" is member, extensive read access
This Active Directory supplement describes using broad legacy access to read sensitive attributes such as LAPS passwords. That is actionable reconnaissance and credential exposure guidance.
Высокий
System reconnaissance
rationale = "Avoid account lockout - spray, don't brute"
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
System reconnaissance
ONLY valid stop condition:
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
System reconnaissance
- Avoid interactive tools (use flags: `-y`, `--non-interactive`)
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
System reconnaissance
→ Each time: Check history to avoid repeating
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Network scanning tools
nmap --script=vuln,discovery -p- TARGET
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Показать все подтверждённые находки (13)
Высокий
Network scanning tools
nmap --script=vuln,discovery -p- TARGET
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Network scanning tools
Re-read nmap output
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Network scanning tools
- Port scanning strategies (nmap, masscan)
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Network scanning tools
4. **Action**: Execute `nmap -p- -T4 10.10.10.1`, update state
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Credential and Active Directory Abuse Playbook
The skill includes repeatable workflows for password spraying, PASSWD_NOTREQD exploitation, skeleton object abuse, LDAP modification, and other Active Directory attack paths.
The files provide concrete credential attack budgets and named AD abuse techniques with protocol-specific steps.
Пункты проверки возможностей (100)
Это реальные локальные возможности, которые могут ожидаться для этого навыка, поэтому они требуют проверки, но не считаются подтверждённым вредоносным поведением.
Критично
Ruby/shell backtick execution
15. **Action**: Trigger shell via `curl http://10.10.10.1/uploads/shell.phtml?cmd=id`
This location directs exploitation that yields command execution or a root shell, such as a webshell trigger or sudo-based shell escape. That is direct offensive capability, not benign documentation.
Критично
Ruby/shell backtick execution
25. **Action**: Exploit via `sudo vim -c ':!/bin/sh'`
This location directs exploitation that yields command execution or a root shell, such as a webshell trigger or sudo-based shell escape. That is direct offensive capability, not benign documentation.
Критично
Unix shell invocation
25. **Action**: Exploit via `sudo vim -c ':!/bin/sh'`
This location directs exploitation that yields command execution or a root shell, such as a webshell trigger or sudo-based shell escape. That is direct offensive capability, not benign documentation.
Критично
sudo privilege escalation
25. **Action**: Exploit via `sudo vim -c ':!/bin/sh'`
This location directs exploitation that yields command execution or a root shell, such as a webshell trigger or sudo-based shell escape. That is direct offensive capability, not benign documentation.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
1. Create or load state file: `.pentest-state.json`
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
3. Set phase to `reconnaissance`
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Ruby/shell backtick execution
```
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
1. **Load current state** from `.pentest-state.json`
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
1. **Update state** with `current_action` description
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
- Search common locations: `/home/*/user.txt`, `/root/root.txt`
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
- Record to `successful_paths` with details
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
- Trigger: Both `user` and `root` flags captured
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```markdown
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
```
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
- Read `user.txt` or equivalent (actual 32-char hex string)
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
- Read `root.txt` or equivalent (actual 32-char hex string)
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
- Avoid interactive tools (use flags: `-y`, `--non-interactive`)
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
```
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Ruby/shell backtick execution
```
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
**Reconnaissance Knowledge** (`.claude/skills/recon/SKILL.md`):
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Ruby/shell backtick execution
**Exploitation Knowledge** (`.claude/skills/exploitation/SKILL.md`):
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
**Privilege Escalation Knowledge** (`.claude/skills/privesc/SKILL.md`):
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
```
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
2. **Initialize**: Create `.pentest-state.json` with target, password_attempts=0, stuck_counter=0
This location is part of the skill’s coordinated reconnaissance, exploitation, and privilege escalation workflow. The context confirms an intended offensive use rather than a benign utility pattern.
Высокий
Ruby/shell backtick execution
4. **Action**: Execute `nmap -p- -T4 10.10.10.1`, update state
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Ruby/shell backtick execution
7. **Action**: Execute `gobuster dir -u http://10.10.10.1 -w /usr/share/wordlists/dirb/common.txt`
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Ruby/shell backtick execution
18. **Action**: Execute `find /home -name user.txt 2>/dev/null`
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
19. **Observation**: Found `/home/alice/user.txt`
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
20. **Action**: Execute `cat /home/alice/user.txt`
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
21. **Observation**: User flag captured: `abc123def456...`, update state
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
23. **Action**: Check `sudo -l`
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
24. **Observation**: Can run `/usr/bin/vim` as root
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
27. **Action**: Execute `cat /root/root.txt`
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
28. **Observation**: Root flag captured: `def456abc123...`, update state
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Ruby/shell backtick execution
```
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```json
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
**See**: `.claude/skills/coordinator/AD_ATTACK_SUPPLEMENT.md` for complete technique lists and comma
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
Ruby/shell backtick execution
```json
This location gives prescriptive credential or Active Directory attack workflow, including password spraying, anomaly exploitation, or repeated authentication testing. That is actionable offensive guidance.
Высокий
Ruby/shell backtick execution
```
This location restricts stopping, status updates, user confirmation, or help requests until flags are captured. That undermines user control while driving offensive actions.
Высокий
sudo privilege escalation
23. **Action**: Check `sudo -l`
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Высокий
Hardcoded URL
7. **Action**: Execute `gobuster dir -u http://10.10.10.1 -w /usr/share/wordlists/dirb/common.txt`
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Hardcoded URL
15. **Action**: Trigger shell via `curl http://10.10.10.1/uploads/shell.phtml?cmd=id`
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Hardcoded IP address
4. **Action**: Execute `nmap -p- -T4 10.10.10.1`, update state
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Hardcoded IP address
7. **Action**: Execute `gobuster dir -u http://10.10.10.1 -w /usr/share/wordlists/dirb/common.txt`
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Hardcoded IP address
15. **Action**: Trigger shell via `curl http://10.10.10.1/uploads/shell.phtml?cmd=id`
This location directs network reconnaissance or web enumeration against a target using tools such as nmap, gobuster, or curl. In this skill context it is part of an autonomous attack workflow.
Высокий
Standard device file access
18. **Action**: Execute `find /home -name user.txt 2>/dev/null`
This location supports post-exploitation activity such as flag discovery, shell handling, or privilege escalation. The surrounding workflow aims to gain user and root access.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
Update `.pentest-state.json` after EVERY action:
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Ruby/shell backtick execution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Shell command substitution
user_flag=$(jq -r '.flags.user' .pentest-state.json)
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Shell command substitution
root_flag=$(jq -r '.flags.root' .pentest-state.json)
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Средний
Template literal with command substitution
```bash
This location instructs the agent to execute local shell commands for state checks or state mutation. The commands are state-focused, but they still create external command execution in a high-risk skill.
Факторы риска
⚙️ Внешние команды (105)
SKILL.md:17-19 SKILL.md:19-53 SKILL.md:53-55 SKILL.md:55-58 SKILL.md:58-86 SKILL.md:86-97 SKILL.md:97-160 SKILL.md:160-163 SKILL.md:163-173 SKILL.md:173-176 SKILL.md:176-191 SKILL.md:191-194 SKILL.md:194-210 SKILL.md:210-213 SKILL.md:213-249 SKILL.md:249-252 SKILL.md:252-273 SKILL.md:273-277 SKILL.md:277-294 SKILL.md:294-296 SKILL.md:296-300 SKILL.md:300-307 SKILL.md:307-310 SKILL.md:310-322 SKILL.md:322 SKILL.md:327-334 SKILL.md:334-344 SKILL.md:344-347 SKILL.md:347-367 SKILL.md:367-370 SKILL.md:370-379 SKILL.md:379-382 SKILL.md:382-390 SKILL.md:390-393 SKILL.md:393-398 SKILL.md:398-411 SKILL.md:411 SKILL.md:426-492 SKILL.md:492-497 SKILL.md:497-504 SKILL.md:504-514 SKILL.md:514-517 SKILL.md:517-525 SKILL.md:525-526 SKILL.md:526-529 SKILL.md:529-530 SKILL.md:530-533 SKILL.md:533-536 SKILL.md:536-573 SKILL.md:573-577 SKILL.md:577 SKILL.md:581-600 SKILL.md:600-603 SKILL.md:603-619 SKILL.md:619-622 SKILL.md:622-646 SKILL.md:646-653 SKILL.md:653-664 SKILL.md:664-667 SKILL.md:667-669 SKILL.md:669-672 SKILL.md:672-688 SKILL.md:688-696 SKILL.md:696-702 SKILL.md:702-708 SKILL.md:708-727 SKILL.md:727-734 SKILL.md:734-743 SKILL.md:743-745 SKILL.md:745-748 SKILL.md:748-760 SKILL.md:760-763 SKILL.md:763-764 SKILL.md:764-765 SKILL.md:765-766 SKILL.md:766-768 SKILL.md:768-769 SKILL.md:769-770 SKILL.md:770-772 SKILL.md:772-773 SKILL.md:773-782 SKILL.md:782-802 SKILL.md:802-827 SKILL.md:827-842 SKILL.md:842-846 SKILL.md:846-865 SKILL.md:865-871 SKILL.md:871-903 SKILL.md:903-917 SKILL.md:917-943 SKILL.md:943-1013 SKILL.md:1013-1020 SKILL.md:1020-1022 SKILL.md:1022-1031 SKILL.md:1031-1046 SKILL.md:1046-1050 SKILL.md:1050-1083 SKILL.md:1083-1086 SKILL.md:1086-1102 SKILL.md:873 SKILL.md:874 SKILL.md:871-903 SKILL.md:770 SKILL.md:768 SKILL.md:770
🌐 Доступ к сети (7)
📁 Доступ к файловой системе (2)
Обнаруженные паттерны
Network reconnaissanceSystem reconnaissance×4Network scanning tools×5
Аудитор:: codex Посмотреть историю аудитов →
Поделиться и цитировать этот отчет
Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.
Копировать ссылку на отчёт
https://skillstore.io/skills/charleskozel-pentest-coordinator/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportЗначок Markdown
[](https://skillstore.io/skills/charleskozel-pentest-coordinator?utm_source=security_passport_badge)Значок HTML
<a href="https://skillstore.io/skills/charleskozel-pentest-coordinator?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/charleskozel-pentest-coordinator/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Встраиваемая карточка
<iframe src="https://skillstore.io/embed/skills/charleskozel-pentest-coordinator.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Академические ссылки (APA · BibTeX · CFF)
Цитата APA
CharlesKozel. (2026). pentest-coordinator security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/charleskozel-pentest-coordinator/audits/8Цитата BibTeX
@techreport{charleskozel-charleskozel-pentest-coordinator-2026,
author = {CharlesKozel},
title = {pentest-coordinator security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/charleskozel-pentest-coordinator/audits/8},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "pentest-coordinator security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "CharlesKozel"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/charleskozel-pentest-coordinator/audits/8"
identifiers:
- type: other
value: "skillstore:charleskozel-pentest-coordinator:audit:8"
description: "Skillstore immutable audit report identifier"
Оценка Skillstore
Почему такая оценка Достоверность доказательств: Средний 55
Архитектура
85
Сопровождаемость
87
Контент
70
Сообщество
70
Соответствие спецификации
Что вы можете построить
Проведение лабораторных упражнений CTF
Провести учащегося через структурированные заметки и отслеживание этапов во время разрешенной задачи capture-the-flag.
Организация внутренних лабораторий Red Team
Отслеживать гипотезы атак, неудачные попытки и пути эскалации в контролируемой корпоративной лаборатории.
Обучение методологии тестирования на проникновение
Показать, как результаты разведки связаны с решениями по эксплуатации и повышению привилегий.
Попробуйте эти промпты
Запуск лаборатории с ограниченной областью
Start an authorized lab assessment for target [target]. Record scope, assumptions, initial phase, and safe stop conditions.
Обзор текущего прогресса
Review my current lab notes. Summarize known services, failed paths, likely next vectors, and any safety concerns.
Планирование исследования AD
Given these authorized Active Directory lab findings, create a prioritized investigation plan with evidence needed for each hypothesis.
Аудит решений по атаке
Evaluate this lab workflow for repeated methods, unsafe assumptions, missing authorization checks, and better defensive documentation.
Лучшие практики
- Используйте навык только против систем, для которых есть письменная авторизация и четко определенная область.
- Добавляйте человеческое подтверждение перед каждым сетевым действием, эксплуатацией, проверкой учетных данных или повышением привилегий.
- Ведите обоснованный аудиторский след результатов, команд, временных меток и решений.
Избегать
- Не используйте навык на публичных или сторонних целях без явного разрешения.
- Не допускайте автономного выполнения без подтверждения пользователя и ограничений скорости.
- Не считайте захват флага более важным, чем безопасность, законность или границы области.
Часто задаваемые вопросы
Безопасно ли использовать этот навык на реальных системах?
Используйте его только при наличии письменной авторизации и определенной области. Текущий навык содержит высокорисковые наступательные рабочие процессы.
Выполняет ли он команды самостоятельно?
Навык инструктирует агента выполнять команды как часть своего рабочего процесса. Перед использованием добавьте механизмы подтверждения.
Может ли он помочь с defensive training?
Да, в контролируемой лаборатории он может показать, как результаты приводят к решениям по эксплуатации и эскалации.
Поддерживает ли он лаборатории Active Directory?
Да. Он включает рабочие процессы для аномалий политики паролей, разрешений объектов, Kerberos и служб сертификатов.
Что пользователям следует подготовить сначала?
Подготовьте письменную авторизацию, область целей, правила лаборатории, ограничения скорости и четкий процесс остановки.
Почему проверка marketplace важна для этого навыка?
Навык сочетает сканирование, эксплуатацию, проверку учетных данных и поведение, препятствующее остановке. Перед публикацией для этого требуются строгие меры защиты.
Сведения для разработчиков
Автор
CharlesKozelЛицензия
MIT
Ревизия Skillstore
r1
Примечание о версии
Автор не указал версию.
Репозиторий
https://github.com/CharlesKozel/vulhub_automated_pentester/tree/main/agents/claude/skills/coordinatorСсылка
dd4a3ef9f20ddf38830950b4bb713df96b431fd6
Актуальность поддержки
22.07.2026
Использование
8 загрузок · 203 просмотров
Структура файлов