Skip to content
TrustedSkillsbeta
Back to all skills

Ctf Web

Listed
ljagiello·vlatest·security·MIT

Automates common web exploitation techniques in CTFs, including XSS, SQLi, and LFI vulnerability detection.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add ljagiello/ctf-skills --skill ctf-web -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

ljagiello

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 12 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: 169.254.169.254, 192.168.1.1, attacker.burpcollaborator.net, attacker.com, exfil.com….

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    target.comundeclaredsuspicious-subdomain.target.comundeclaredattacker.comundeclaredwebhook.siteundeclared192.168.1.1undeclaredtrusted.comundeclaredexfil.comundeclared127.0.0.1local169.254.169.254undeclaredschemas.openxmlformats.orgnamespace identifierwww.w3.orgstandardsjava.sun.comundeclaredattacker.burpcollaborator.netundeclaredwww.google.comundeclaredwww.bing.comundeclared

    What it found (3 of 47)

    • ctf-web/SKILL.md:116contacts target.com
      curl -sI https://target.com
    • ctf-web/SKILL.md:118contacts target.com
      curl -s https://target.com/robots.txt
    • ctf-web/SKILL.md:131contacts target.com
      curl "https://target.com/page?name={{7*7}}"

  • No credential access: failed

    Touches credential material in 2 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found

    • ctf-web/cves.md:342SSH private keys or config
      -e "SELECT load_file('/backup/id_rsa')"
    • ctf-web/server-side-advanced-2.md:555SSH private keys or config
      /home/user/.ssh/id_rsa         # SSH private keys

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned ljagiello/ctf-skills at c332c7be1b.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
c332c7be1b
Manifest
ctf-web/SKILL.md
Scanned
24 files, 9,155 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

The ctf-web skill enables AI agents to interact with web-based Capture The Flag (CTF) challenges, automating the process of exploring pages, analyzing code, and solving puzzles. It is designed specifically for platforms like HackTheBox or TryHackMe where solutions often require navigating dynamic web interfaces rather than just reading text files.

When to use it

  • Automating walkthroughs for beginner-friendly web CTF challenges on platforms like HackTheBox.
  • Solving logic-based puzzles that require clicking through multiple pages to find hidden flags.
  • Testing AI agents' ability to handle interactive browser environments and form submissions.
  • Practicing red teaming techniques in a safe, gamified environment without manual navigation.

Key capabilities

  • Navigating multi-step web challenges that require sequential actions.
  • Identifying and extracting hidden flags from page source or dynamic content.
  • Executing specific click sequences to trigger puzzle solutions.
  • Handling interactive elements like forms, dropdowns, and modals within CTF contexts.

Example prompts

  • "Navigate to the first level of this HackTheBox web challenge and find the flag."
  • "Click through the login page, enter the provided credentials, and extract the session token."
  • "Analyze the source code of this webpage to locate a hidden comment containing the solution."

Tips & gotchas

Ensure the AI agent has access to a browser environment capable of executing JavaScript interactions, as static analysis alone may not solve dynamic challenges. Some CTF platforms require human verification or CAPTCHA bypassing, which this skill may not fully automate without additional tools.