ctf-web

Web CTF challenge triage and active interaction workflow.

IndexedMIT

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/onesword-ai-ctf-web

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Web CTF challenge triage and active interaction workflow. Use for HTTP/HTTPS targets, web source code, login/forms, API endpoints, cookies, SSRF, SQL injection, SSTI, LFI/RFI, upload, path traversal, auth bypass, and response-based flag extraction.

Use cases: backend, security, productivity

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/ctf-web

What's inside

Skill name: ctf-web
Description: Web CTF challenge triage and active interaction workflow. Use for HTTP/HTTPS targets, web source code, login/forms, API endpoints, cookies, SSRF, SQL injection, SSTI, LFI/RFI, upload, path traversal, auth bypass, and response-based flag extraction.
License: MIT
Instructions: 19 lines in SKILL.md · view on GitHub

Files (2)

SKILL.md
openai.yaml · agents/

SKILL.md (first lines)

# CTF Web

## Workflow

1. Normalize targets: identify base URL, exposed ports, path hints, credentials, cookies, and source files.
2. Establish baselines with bounded GET requests for `/`, common paths, linked resources, and obvious endpoints.
3. Detect forms, links with parameters, APIs, redirects, status changes, cookies, and response length changes.
4. Try limited active probes: form submission, SQL error payloads, SSTI arithmetic, path traversal, LFI markers, and simple auth bypass values.
5. Extract candidate flags from every response body and relevant headers.

## Evidence Rules

Record URL, method, payload, status, body length, response markers, and extracted flag source. Treat memory or known challenge patterns as hints only. Do not confirm a flag without direct response evidence.

## Output

Return structured findings, candidate flags, tool outputs, and next actions. If no flag is found, publish the most suspicious endpoint or parameter for follow-up instead of repeating the same probes.

From OneSword-AI/CyberAgent, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Aug 18, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/OneSword-AI/CyberAgent
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from OneSword-AI

Cite this page

ctf-web skill. Agent Mart. https://agentmart.dev/skills/onesword-ai-ctf-web (last updated 2026-10-24)