Agent skill · data analytics · sickn33
ffuf-claude-skill
Web fuzzing with ffuf
Why this skill is useful
Codifies specific patterns and guidance for web fuzzing with ffuf that the AI could infer but doesn't have to guess.
What it needs
About 1k tokens when loaded. Last updated 2026-08-07. 44,571 stars on the source repository.
What this skill does
Ffuf Claude Skill ⚠️ AUTHORIZED USE ONLY This skill is for educational purposes or authorized security assessments only. You must have explicit, written permission from the system owner before using this tool. Misuse of this tool is illegal and strictly prohibited. Overview Web fuzzing with ffuf When to Use This Skill Use this skill when you need to work with web fuzzing with ffuf. Instructions Use only a specifically authorized fuzzing target and allowed paths. Record host, protocol, scope, time window, request-rate limits and prohibited side effects before sending traffic. This AAS entrypoint does not bundle ffuf, a wordlist or an upstream runner. Inspect the installed version's help and review the selected wordlist. Plan a bounded run against a local or explicitly authorized test environment; avoid writes, authenticated-state changes and rate-limit bypass. Compare candidate responses with a known missing-path baseline; response size/status alone does not prove a vulnerability. Preserve request/response evidence after redacting secrets, stop on target instability or scope changes, and report untested paths as unknown. Mandatory confirmation gate Before each probing command, collect the exact target URL, IP, account, or resource, written authorization and permitted scope. Show the exact command and expected effect. Wait for explicit confirmation in the current conversation. Without confirmation, remain read-only and provide defensive guidance only. No traffic is authorized simply by invoking this guide. Example User request: Use @ffuf-claude-skill for this task: Web fuzzing with ffuf. Limitations Use this skill only when the task clearly matches the scope described above. Do not treat the output as a substitute for environment-specific validation, testing, or expert review. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sickn33/ffuf-claude-skill