Fähigkeiten skill-permissions
📦

skill-permissions

Inhaltsrevision r1 Hohes Risiko ⚙️ Externe Befehle📁 Dateisystemzugriff

Аудит разрешений навыков

Навыкам Claude Code могут требоваться разрешения shell, которые сложно проверять вручную. Этот навык анализирует заявленное использование команд и помогает создавать соответствующие записи allowlist с предупреждениями о широких изменениях.

Unterstützt: Claude Codex Code(CC)
⚠️ 38 Schlecht

Mit meinem Agent installieren

Kopieren Sie diese Anfrage in Ihren Agent. Sie enthält die maßgebliche Skill-Seite und das Manifest.

Agent-Anfrage
Review the Skillstore skill "skill-permissions" from https://skillstore.io/skills/guo-yu-skill-permissions.md and its manifest at https://skillstore.io/api/skills/guo-yu-skill-permissions/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Ihr Agent sollte weiterhin seinen Plan anzeigen und alle von der Sicherheitsrichtlinie verlangten Bestätigungen anfordern.

Agent-lesbare Ressourcen

Verwenden Sie diese Links, wenn ein KI-Agent, Crawler oder Skript sauberen Kontext benötigt, statt die vollständige Seite zu lesen.

Markdown-Detailseite GET /skills/guo-yu-skill-permissions.md Signiertes manifest GET /api/skills/guo-yu-skill-permissions/manifest Signiertes lockfile GET /api/skills/guo-yu-skill-permissions/lockfile

Testen

„skill-permissions“ wird verwendet. Проанализируй навык port-allocator.

Erwartetes Ergebnis:

  • Перечисляет обнаруженные команды, такие как find, ls, cat и lsof.
  • Показывает предложенные правила Claude Code allow.
  • Рекомендует конкретную команду allow для этого навыка.

„skill-permissions“ wird verwendet. Покажи разрешения для всех навыков.

Erwartetes Ergebnis:

  • Отображает таблицу установленных навыков и основных групп разрешений.
  • Отмечает навыки, которым требуется авторизация.
  • Предлагает проверить результаты перед пакетной авторизацией.

„skill-permissions“ wird verwendet. Авторизуй один проверенный навык.

Erwartetes Ergebnis:

  • Сообщает, что правила разрешений были объединены.
  • Показывает затронутый файл настроек.
  • Напоминает пользователю, что разрешения применяются в новой сессии или после очистки.

Sicherheitsaudit

Hohes Risiko
v6 • 9.7.2026 Versionsbericht öffnen

The skill is a security-sensitive permission management helper, not malware. Most dangerous command hits are documented blocklist examples, but the skill can broaden Claude Code Bash allow rules and batch-modify settings or skill files, so publication should require strong warnings and safer defaults.

3
Gescannte Dateien
894
Analysierte Zeilen
115
Prüfelemente
0
Falschmeldungen ignoriert

Bestätigte Sicherheitsbedenken (4)

Hoch
SKILL.md:16-18SKILL.zh-CN.md:156-188
Batch Permission Expansion and Skill File Modification
The skill documents allow-all and inject modes that can modify settings.json or add allow commands across installed skills. This creates broad local permission expansion risk even though the documentation warns users.
The behavior is explicitly described in multiple language files and affects configuration plus many skill files. The warnings reduce surprise but do not remove the risk.
Hoch
SKILL.md:201-210SKILL.zh-CN.md:429-438
Overbroad Claude Directory Allow Rules
The generated allow rules include broad access to ~/.claude paths, including Bash(cat ~/.claude/*). These rules can expose sensitive local Claude configuration if granted too broadly.
The allow rules are shown directly in the documented authorization flow. The risk depends on user approval, but the scope is broad and security-sensitive.
Mittel
SKILL.md:23
System reconnaissance
- Avoid `inject` or `allow-all` unless you understand the impact
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.md:217
System reconnaissance
1. **Conservative analysis** - Only identify explicitly appearing commands, avoid over-authorization
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Elemente der Fähigkeitsprüfung (115)

Dies sind echte lokale Fähigkeiten, die für diese Fähigkeit erwartet werden können; daher müssen sie überprüft werden, werden jedoch nicht als bestätigtes bösartiges Verhalten gezählt.

Hoch
SKILL.ja.md:47
Hidden file in home directory
cat ~/.claude/* → Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:67
Hidden file in home directory
"Bash(cat ~/.claude/*)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:82
Hidden file in home directory
find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:126
Hidden file in home directory
場所: ~/.claude/skills/port-allocator
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:136
Hidden file in home directory
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:150
Hidden file in home directory
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:152
Hidden file in home directory
設定ファイル: ~/.claude/settings.json
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:159
Hidden file in home directory
- **権限設定**: `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:160
Hidden file in home directory
- **スキルディレクトリ**: `~/.claude/skills/`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:173
Hidden file in home directory
1. `~/.claude/settings.json` を読み取り
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:180
Hidden file in home directory
"Bash(find ~/.claude/skills *)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.ja.md:181
Hidden file in home directory
"Bash(cat ~/.claude/*)"
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:47
Hidden file in home directory
cat ~/.claude/* → Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:68
Hidden file in home directory
"Bash(cat ~/.claude/*)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:83
Hidden file in home directory
find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:100
Hidden file in home directory
SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:148
Hidden file in home directory
Location: ~/.claude/skills/port-allocator
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:159
Hidden file in home directory
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:174
Hidden file in home directory
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:177
Hidden file in home directory
Config file: ~/.claude/settings.json
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:184
Hidden file in home directory
- **Permission config**: `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:185
Hidden file in home directory
- **Skill directory**: `~/.claude/skills/`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:198
Hidden file in home directory
1. Read `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:205
Hidden file in home directory
"Bash(find ~/.claude/skills *)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.md:206
Hidden file in home directory
"Bash(cat ~/.claude/*)"
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:47
Hidden file in home directory
cat ~/.claude/* → Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:68
Hidden file in home directory
"Bash(cat ~/.claude/*)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:93
Hidden file in home directory
find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:123
Hidden file in home directory
SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:138
Hidden file in home directory
cat ~/.claude/settings.json 2>/dev/null || echo '{"permissions":{"allow":[]}}'
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:171
Hidden file in home directory
1. 读取 `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:198
Hidden file in home directory
| `cat ~/.claude/*` | `Bash(cat ~/.claude/*)` |
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:273
Hidden file in home directory
📁 位置: ~/.claude/skills/dangerous-skill
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:284
Hidden file in home directory
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:316
Hidden file in home directory
📁 位置: ~/.claude/skills/port-allocator
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:328
Hidden file in home directory
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:359
Hidden file in home directory
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:363
Hidden file in home directory
配置文件: ~/.claude/settings.json
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:382
Hidden file in home directory
- **权限配置**: `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:383
Hidden file in home directory
- **skill 目录**: `~/.claude/skills/`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:426
Hidden file in home directory
1. 读取 `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:433
Hidden file in home directory
"Bash(find ~/.claude/skills *)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:434
Hidden file in home directory
"Bash(cat ~/.claude/*)"
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:459
Hidden file in home directory
- Bash(find ~/.claude/skills *)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:460
Hidden file in home directory
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Hoch
SKILL.zh-CN.md:462
Hidden file in home directory
配置文件: ~/.claude/settings.json
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:47
Hidden file access
cat ~/.claude/* → Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:67
Hidden file access
"Bash(cat ~/.claude/*)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:82
Hidden file access
find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:126
Hidden file access
場所: ~/.claude/skills/port-allocator
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:136
Hidden file access
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:150
Hidden file access
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:152
Hidden file access
設定ファイル: ~/.claude/settings.json
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:159
Hidden file access
- **権限設定**: `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:160
Hidden file access
- **スキルディレクトリ**: `~/.claude/skills/`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:173
Hidden file access
1. `~/.claude/settings.json` を読み取り
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:180
Hidden file access
"Bash(find ~/.claude/skills *)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.ja.md:181
Hidden file access
"Bash(cat ~/.claude/*)"
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:16
Ruby/shell backtick execution
| `/skill-permissions inject` | High | Batch modify all skill SKILL.md files |
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.md:17
Ruby/shell backtick execution
| `/skill-permissions allow-all` | Medium | Batch modify settings.json |
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.md:23
Ruby/shell backtick execution
- Avoid `inject` or `allow-all` unless you understand the impact
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.md:30
Ruby/shell backtick execution
| `/skill-permissions` | Analyze all skills and show permission summary |
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.md:33
Ruby/shell backtick execution
| `/skill-permissions allow-all` | Execute one-time authorization for all skills |
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.md:34
Ruby/shell backtick execution
| `/skill-permissions inject` | Inject allow command into all skills |
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.md:60-62
Ruby/shell backtick execution
Convert identified commands to `permissions.allow` rules:
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:184-185
Ruby/shell backtick execution
- **Permission config**: `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:185-190
Ruby/shell backtick execution
- **Skill directory**: `~/.claude/skills/`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:198-199
Ruby/shell backtick execution
1. Read `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:199-201
Ruby/shell backtick execution
2. Merge the following permissions to `permissions.allow`:
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:100
Shell command substitution
SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:47
Hidden file access
cat ~/.claude/* → Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:68
Hidden file access
"Bash(cat ~/.claude/*)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:83
Hidden file access
find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:100
Hidden file access
SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:148
Hidden file access
Location: ~/.claude/skills/port-allocator
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:159
Hidden file access
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:174
Hidden file access
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:177
Hidden file access
Config file: ~/.claude/settings.json
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:184
Hidden file access
- **Permission config**: `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:185
Hidden file access
- **Skill directory**: `~/.claude/skills/`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:198
Hidden file access
1. Read `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:205
Hidden file access
"Bash(find ~/.claude/skills *)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.md:206
Hidden file access
"Bash(cat ~/.claude/*)"
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:147-156
Ruby/shell backtick execution
### 命令: `/skill-permissions allow-all`
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.zh-CN.md:156-158
Ruby/shell backtick execution
### 命令: `/skill-permissions inject`
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.zh-CN.md:158-163
Ruby/shell backtick execution
为所有 skill 注入 `allow` 子命令:
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.zh-CN.md:198
Ruby/shell backtick execution
| `cat ~/.claude/*` | `Bash(cat ~/.claude/*)` |
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:309-314
Ruby/shell backtick execution
- `allow_override`: 从默认黑名单中移除的命令(谨慎使用)
The documentation allows users to remove patterns from the default blocklist. That is intentional configuration, but it can weaken safeguards around dangerous commands.
Mittel
SKILL.zh-CN.md:382-383
Ruby/shell backtick execution
- **权限配置**: `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:383-389
Ruby/shell backtick execution
- **skill 目录**: `~/.claude/skills/`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:416-417
Ruby/shell backtick execution
1. **文件修改风险** - `inject` 命令会修改所有 skill 的 SKILL.md 文件
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.zh-CN.md:417-420
Ruby/shell backtick execution
2. **权限扩大风险** - `allow-all` 会为所有 skill 添加权限,可能授予过多权限
The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.
Mittel
SKILL.zh-CN.md:426-427
Ruby/shell backtick execution
1. 读取 `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:427-429
Ruby/shell backtick execution
2. 合并以下权限到 `permissions.allow`:
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:47
Hidden file access
cat ~/.claude/* → Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:68
Hidden file access
"Bash(cat ~/.claude/*)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:93
Hidden file access
find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:123
Hidden file access
SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:138
Hidden file access
cat ~/.claude/settings.json 2>/dev/null || echo '{"permissions":{"allow":[]}}'
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:171
Hidden file access
1. 读取 `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:198
Hidden file access
| `cat ~/.claude/*` | `Bash(cat ~/.claude/*)` |
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:273
Hidden file access
📁 位置: ~/.claude/skills/dangerous-skill
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:284
Hidden file access
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:316
Hidden file access
📁 位置: ~/.claude/skills/port-allocator
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:328
Hidden file access
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:359
Hidden file access
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:363
Hidden file access
配置文件: ~/.claude/settings.json
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:382
Hidden file access
- **权限配置**: `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:383
Hidden file access
- **skill 目录**: `~/.claude/skills/`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:426
Hidden file access
1. 读取 `~/.claude/settings.json`
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:433
Hidden file access
"Bash(find ~/.claude/skills *)",
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:434
Hidden file access
"Bash(cat ~/.claude/*)"
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:459
Hidden file access
- Bash(find ~/.claude/skills *)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:460
Hidden file access
- Bash(cat ~/.claude/*)
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.
Mittel
SKILL.zh-CN.md:462
Hidden file access
配置文件: ~/.claude/settings.json
The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.

Risikofaktoren

⚙️ Externe Befehle (50)
SKILL.ja.md:138-139 SKILL.ja.md:107 SKILL.md:16 SKILL.md:17 SKILL.md:18 SKILL.md:19 SKILL.md:22 SKILL.md:23 SKILL.md:24 SKILL.md:30 SKILL.md:31 SKILL.md:32 SKILL.md:33 SKILL.md:34 SKILL.md:35 SKILL.md:44-51 SKILL.md:51-54 SKILL.md:54 SKILL.md:55-60 SKILL.md:60-62 SKILL.md:62-73 SKILL.md:73-77 SKILL.md:77-82 SKILL.md:82-84 SKILL.md:84-94 SKILL.md:94-99 SKILL.md:99-101 SKILL.md:101-107 SKILL.md:107-124 SKILL.md:124-125 SKILL.md:125-126 SKILL.md:126-127 SKILL.md:127-132 SKILL.md:132-133 SKILL.md:133-134 SKILL.md:134-135 SKILL.md:135-140 SKILL.md:140-141 SKILL.md:141-146 SKILL.md:146-162 SKILL.md:162-163 SKILL.md:163-166 SKILL.md:166-180 SKILL.md:180-184 SKILL.md:184-185 SKILL.md:185-190 SKILL.md:190-192 SKILL.md:192-194 SKILL.md:194-198 SKILL.md:198-199
📁 Dateisystemzugriff (50)
SKILL.ja.md:47 SKILL.ja.md:67 SKILL.ja.md:82 SKILL.ja.md:126 SKILL.ja.md:131 SKILL.ja.md:136 SKILL.ja.md:150 SKILL.ja.md:152 SKILL.ja.md:159 SKILL.ja.md:160 SKILL.ja.md:173 SKILL.ja.md:180 SKILL.ja.md:181 SKILL.ja.md:47 SKILL.ja.md:67 SKILL.ja.md:82 SKILL.ja.md:126 SKILL.ja.md:131 SKILL.ja.md:136 SKILL.ja.md:150 SKILL.ja.md:152 SKILL.ja.md:159 SKILL.ja.md:160 SKILL.ja.md:173 SKILL.ja.md:180 SKILL.ja.md:181 SKILL.ja.md:82 SKILL.md:47 SKILL.md:68 SKILL.md:83 SKILL.md:100 SKILL.md:148 SKILL.md:153 SKILL.md:159 SKILL.md:174 SKILL.md:177 SKILL.md:184 SKILL.md:185 SKILL.md:198 SKILL.md:205 SKILL.md:206 SKILL.md:47 SKILL.md:68 SKILL.md:83 SKILL.md:100 SKILL.md:148 SKILL.md:153 SKILL.md:159 SKILL.md:174 SKILL.md:177

Erkannte Muster

System reconnaissance×2
Geprüft von: claude Audit-Verlauf anzeigen →
Diesen Bericht teilen & zitieren

Teile den versionierten Bewertungsbericht, das neutrale Badge, die Einbettungskarte und Zitate. Skillstore berichtet Nachweise, ohne zu entscheiden, ob dieser Skill sicher ist.

Versionsbericht öffnen
Sicherheitsbewertung

Berichtslink kopieren

https://skillstore.io/skills/guo-yu-skill-permissions/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown-Badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/guo-yu-skill-permissions/security.svg)](https://skillstore.io/skills/guo-yu-skill-permissions?utm_source=security_passport_badge)

HTML-Badge

<a href="https://skillstore.io/skills/guo-yu-skill-permissions?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/guo-yu-skill-permissions/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Einbettungskarte

<iframe src="https://skillstore.io/embed/skills/guo-yu-skill-permissions.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Wissenschaftliche Zitate (APA · BibTeX · CFF)

APA-Zitat

guo-yu. (2026). skill-permissions security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/guo-yu-skill-permissions/audits/6

BibTeX-Zitat

@techreport{guo-yu-guo-yu-skill-permissions-2026, author = {guo-yu}, title = {skill-permissions security audit report (audit version 6)}, institution = {Skillstore}, year = {2026}, number = {6}, url = {https://skillstore.io/skills/guo-yu-skill-permissions/audits/6}, 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: "skill-permissions security audit report (audit version 6)" version: "unspecified" type: report authors: - name: "guo-yu" date-released: "2026-07-09" url: "https://skillstore.io/skills/guo-yu-skill-permissions/audits/6" identifiers: - type: other value: "skillstore:guo-yu-skill-permissions:audit:6" description: "Skillstore immutable audit report identifier"

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel
55
Architektur
85
Wartbarkeit
87
Inhalt
71
Gemeinschaft
83
Spezifikationskonformität

Was Sie erstellen können

Проверить новый навык сообщества

Проанализируйте один загруженный навык перед предоставлением разрешений Claude Code Bash.

Подготовить локальный набор навыков

Сведите разрешения по установленным навыкам перед командной сессией настройки.

Задокументировать потребности в разрешениях

Сгенерируйте рекомендации по командам allow, объясняющие, какие разрешения требуются навыку.

Diese Prompts ausprobieren

Проанализировать один навык 
Используй skill-permissions, чтобы проанализировать разрешения, требуемые <skill-name>, и объясни каждое запрошенное разрешение.
Проверить перед авторизацией 
Запусти анализ разрешений навыка для <skill-name> в режиме только для чтения. Не изменяй настройки, пока я не одобрю предложенные правила allow.
Проверить все установленные навыки 
Проанализируй все установленные навыки Claude Code и сгруппируй результаты по низкому, среднему и высокому риску разрешений.
Спланировать контролируемую авторизацию 
Проанализируй все навыки, определи разрешения, которые не следует утверждать автоматически, и подготовь явные команды allow только для проверенных навыков.

Bewährte Praktiken

  • Запускайте анализ только для чтения перед использованием любой команды авторизации.
  • Предпочитайте явную авторизацию для каждого навыка вместо режимов allow-all или inject.
  • Проверяйте сгенерированные разрешения с подстановочными символами перед добавлением их в settings.json.

Vermeiden

  • Не запускайте пакетную авторизацию для непроверенных навыков сообщества.
  • Не считайте сгенерированные правила allow доказательством того, что навык безопасен.
  • Не внедряйте команды allow во множество файлов навыков без контроля версий или резервных копий.

Häufig gestellte Fragen

Выполняет ли этот навык обнаруженные команды?
Документированный поток анализа сканирует файлы навыков и генерирует правила разрешений. Команды авторизации изменяют настройки Claude Code.
Почему этот навык чувствителен с точки зрения безопасности?
Он может добавлять правила Bash allow и изменять настройки или документацию навыков в пакетных режимах.
Следует ли мне использовать allow-all?
Используйте allow-all только после проверки каждого сгенерированного разрешения. Авторизация по отдельным навыкам безопаснее.
Может ли он обнаруживать вредоносные навыки?
Он может подсвечивать опасные шаблоны команд, но не заменяет полноценную проверку безопасности.
Какие файлы он затрагивает?
В документации упоминаются ~/.claude/settings.json и установленные файлы навыков в ~/.claude/skills.
Когда применяются новые разрешения?
Навык указывает, что обновления разрешений применяются в новой сессии или после запуска /clear.

Entwicklerdetails

Autor

guo-yu

Lizenz

MIT

Skillstore-Revision

r1

Versionshinweis

Der Autor hat keine Version angegeben.

Repository

https://github.com/guo-yu/skills/tree/master/skill-permissions

Ref.

1ffa7643651792ccb4bd3b15d924d2c97edff755

Aktualität der Wartung

28.7.2026

Nutzung

5 Downloads · 275 Aufrufe

Dateistruktur

📄 SKILL.ja.md

📄 SKILL.md

📄 SKILL.zh-CN.md