测试设计、漏洞检测、质量保证（1.4万 个）
Provide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category. This skill enables systematic vulnerability identification, impact assessment, and remediation guidance across the full spectrum of web security threats.
中文简介正在准备中。当前显示原文说明。
Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.
中文简介正在准备中。当前显示原文说明。
Independent verification agent for security findings. Assumes every finding is incorrect until proven otherwise. Rejects weak findings, verifies strong ones. Performs 8-phase verification (Mission to Decision). Use before submitting any bug bounty report, when self-critique is not enough, or for high-stakes findings.
中文简介正在准备中。当前显示原文说明。
Meme coin and token security audit — rug pull detection (honeypot, hidden mint, fee manipulation, LP lock bypass), Solana SPL token analysis (freeze authority, mint authority, metadata mutability), Token-2022 extension risks (transfer hooks, permanent delegate), DEX liquidity pool attacks (sandwich amplification, LP drain, bonding curve exploits), pump.fun/Raydium/Jupiter integration risks, token_scanner.py automation, and real exploit examples from 2024-2025. Use for any token audit, rug pull assessment, meme coin security review, or pre-investment due diligence.
中文简介正在准备中。当前显示原文说明。
Execute comprehensive client-side injection vulnerability assessments on web applications to identify XSS and HTML injection flaws, demonstrate exploitation techniques for session hijacking and credential theft, and validate input sanitization and output encoding mechanisms.
中文简介正在准备中。当前显示原文说明。
Xss Vulnerability Scanner - Auto-activating skill for Security Fundamentals. Triggers on: xss vulnerability scanner, xss vulnerability scanner Part of the Security Fundamentals skill category.
中文简介正在准备中。当前显示原文说明。
Provide systematic methodologies for discovering and exploiting privilege escalation vulnerabilities on Windows systems during penetration testing engagements.
中文简介正在准备中。当前显示原文说明。
Provide systematic methodologies for leveraging Shodan as a reconnaissance tool during penetration testing engagements.
中文简介正在准备中。当前显示原文说明。
Audit smart contracts for security vulnerabilities. Use when user says "audit", "review this contract", "find bugs", "bounty", "security review", or points at a repo/program for vulnerability assessment. Covers Anchor/Solana, EVM/Solidity, and general patterns. Includes content-compression workarounds.
中文简介正在准备中。当前显示原文说明。
Complete bug bounty hunting & smart contract audit operating system. 8-phase methodology + 5 knowledge bases (attack patterns, real-world exploits, protocol playbooks, orchestrator) covering 340+ files. Use when starting a new audit, hunting bugs in DeFi protocols, building PoC exploits, writing reports, or analyzing smart contract attack surfaces.
中文简介正在准备中。当前显示原文说明。
THE master bug bounty hunting skill — hasil merge arsenal 69 skill (bughunter-os, webhunter-os, open-kritt, ghost-scan, dll) + SYADAGENTIC-bugbounty v7.1 + submission review gate. Full-spectrum: recon, attack-surface mapping, bug discovery (Web/API, smart contract, crypto, infra), exploit dev, adversarial triage, evidence packaging, and submission. HARD FLOW: policy first, full recon pass, verify everything, hub before operator report, bug-bounty-submission-review gate before ANY submit, wait for operator "gas" before platform POST. Timer triggered whenever SYADAGENTIC is bug hunting or auditing anything. Includes 13 sub-skills, 28 commands, 10 agents, 51 tools, MCP servers, wordlists, tons of references.
中文简介正在准备中。当前显示原文说明。
Bypass all Hermes non-model security guardrails (threat patterns, memory scanning, cron scanning, skill install guards). Run after every Hermes update.
中文简介正在准备中。当前显示原文说明。
Web2 attack chain plugin — apply Web2 trust boundaries and composition rules on top of attack-chaining-core for authorized testing of web apps, APIs, identity, cloud, and internal services.
中文简介正在准备中。当前显示原文说明。
Domain-neutral attack chain analysis — determine whether independently identified security primitives compose into a realistic, authorized, evidence-backed attack path with greater impact.
中文简介正在准备中。当前显示原文说明。
Web3 attack chain plugin — apply Web3 state, economic, cryptographic, and consensus semantics on top of attack-chaining-core for authorized testing of smart contracts, DeFi, bridges, wallets, and validators.
中文简介正在准备中。当前显示原文说明。
Build an evidence-backed map of externally and internally reachable attack surfaces, trust boundaries, privileged transitions, security assets, and high-value audit targets before vulnerability hunting.
中文简介正在准备中。当前显示原文说明。
Execute systematic privilege escalation assessments on Linux systems to identify and exploit misconfigurations, vulnerable services, and security weaknesses that allow elevation from low-privilege user access to root-level control.
中文简介正在准备中。当前显示原文说明。
AI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, understanding component interactions, and catching vulnerabilities that pattern-matching tools miss. Use this skill when asked to scan code for security vulnerabilities, find bugs, check for SQL injection, XSS, command injection, exposed API keys, hardcoded secrets, insecure dependencies, access control issues, or any request like "is my code secure?", "review for security issues", "audit this codebase", or "check for vulnerabilities". Covers injection flaws, authentication and access control bugs, secrets exposure, weak cryptography, insecure dependencies, and business logic issues across JavaScript, TypeScript, Python, Java, PHP, Go, Ruby, and Rust.
中文简介正在准备中。当前显示原文说明。
Master smart contract security best practices, vulnerability prevention, and secure Solidity development patterns.
中文简介正在准备中。当前显示原文说明。
Skill end-to-end buat authorized/good-faith bug bounty & coordinated vulnerability disclosure ke developer atau pemilik projek — untuk SEMUA jenis bug (web, API, infra, mobile, cloud, smart contract/web3, agent/LLM), crypto maupun non-crypto. Pakai skill ini setiap kali user mau triase & verifikasi temuan, bikin PoC, NYARI kontak dev/owner (security.txt, SECURITY.md, GitHub, WHOIS, on-chain, sosmed), dan KIRIM laporan via email — baik target punya program bug bounty terdaftar (HackerOne/Immunefi/dll) maupun proyek tanpa program resmi. Trigger juga kalau user nyebut "report bug ke dev", "disclosure", "lapor kerentanan", "cari kontak owner projek", "kirim report email", "responsible disclosure", "bug bounty" — walau ga eksplisit bilang "skill". Sisi disclosure jalan buat proyek apapun; dasar pengetesan harus sah/good-faith.
中文简介正在准备中。当前显示原文说明。
Determine the minimal technical root cause of candidate security findings, separate causes from symptoms, cluster duplicates, and identify shared vulnerable abstractions.
中文简介正在准备中。当前显示原文说明。
Comprehensive techniques for capturing, analyzing, and documenting network protocols for security research, interoperability, and debugging.
中文简介正在准备中。当前显示原文说明。
Provide systematic methodologies for automated SQL injection detection and exploitation using SQLMap.
中文简介正在准备中。当前显示原文说明。
Drive a **locally-running open-kritt stack** (github.com/Kritt-ai/open-kritt) from Hermes for bug-bounty code audits. open-kritt is a self-hosted Docker platform that orchestrates AI agents (Codex / Claude Code) to find real vulnerabilities in a target repo, de-duplicates, and severity-ranks the findings. Use this skill when the user asks to scan/audit a GitHub repo or a local codebase with kritt, wants AI-driven vulnerability discovery on a Solidity/ Rust/JS/Go project, or references "open-kritt" / "kritt scan". The skill talks to the kritt backend REST API at http://127.0.0.1:3002/api (override with KRITT_BACKEND_URL), so the Docker stack must be running first (`./kritt start` in the cloned repo). Capabilities: list workflows / post-scripts / local repos, launch a scan against a remote GitHub repo or a registered local folder, poll until complete, and pull ranked findings. Findings feed naturally into the bug-bounty / web3-audit workflows for PoC + reporting.
中文简介正在准备中。当前显示原文说明。