Yotta Security Testing — Security skill for Claude Code
YuanCe (元测) — disciplined authorization-first security-testing methodology for AI agents: four-stage web security testing on authorized targets (SRC bug bounty / CTF / self-owned / labs) with built-in.
How to install Yotta Security Testing
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open YottaMeta/yotta-security-testing and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Yotta Security Testing does
YuanCe (元测) — disciplined authorization-first security-testing methodology for AI agents: four-stage web security testing on authorized targets (SRC bug bounty / CTF / self-owned / labs) with built-in Scope Guard (allowlist, target triage, blacklist, audit trail, legal redlines); zero executable payloads. Part of YottaSkills.
Alternatives in Security
- Mcp-scan (Invariant Labs) — MCP security scanner with proxy mode for real-time scanning without infrastructure changes 1.9k ★
- /web3 Audit — Smart contract security audit using the 10-bug-class methodology 927 ★
- Maestro Knowledge — Intent-driven knowledge-store and Run knowledge lifecycle management — audit/prune, stage candidates (with sig 530 ★
README
Language: English · 中文
yotta-security-testing · 元测 (YuanCe)
YottaMeta's disciplined, authorization-first security-testing methodology for Agent skills: a four-stage workflow — Reconnaissance → Discovery → Verification → Reporting — for web security testing on authorized targets only (self-owned assets, SRC / bug-bounty scope, CTF and local training labs), backed by a built-in Scope Guard that turns "authorized only" into a hard mechanism instead of a disclaimer.
Triggers when the user asks for security testing / penetration testing / vulnerability assessment on an authorized target, SRC bug bounty, CTF or lab drills (DVWA / OWASP Juice Shop / HTB / VulnHub), or a vulnerability assessment / pentest report; or says 元测 / security test / pentest / bug bounty / authorized test / scope check.
Zero dependencies (Python 3.8+ standard library); Windows + Linux + macOS; methodology and education oriented — no executable payloads.
An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Code Four reusable dynamic-workflow templates for Claude Code (multi-dimension review, exhaustive audit, budget-sca All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, T Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — 18 vuln classes, no 18 Claude Code skill files for smart contract security — built from 2,749 Immunefi reports, 681 DeFiHack repro Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, Use ONLY for authorized security work — pentesting engagements with written scope, CTF challenges, red-team ex AUTHORIZATION: All targets are LOCAL LAB/CTF environments. Complete authorization. Delegates to this agent when the user is working on CTF challenges, capture the flag competitions, HackTheBox
Related Skills
RedteamAgent
Security community
Claude Code Dynamic Workflows
Security community
Bountyforge
Security community
Public Skills Builder
Security community
Web3 Bug Bounty Hunting AI Skills
Security community
0x002132 Skills Bugbounty Bb Local Toolkit
Security community
Related Agents
Security Lead
Security community
Operator Core
Development community
Ctf Solver
Development community