3,343 件 ・ 関連度順
概要と使いどころ
Exploit AI applications using Indirect Prompt Injection. This skill focuses on hiding malicious instructions within data sources (web pages, documents, emails) that the LLM processes, causing the AI to execute unintended actions or leak data without direct user interaction.
日本語の概要は準備中です。原文の説明を表示しています。
Test Large Language Models for direct prompt injection vulnerabilities where user input overrides system instructions, extracts system prompts, bypasses safety filters, or causes unauthorized actions. Use this skill when assessing chatbots, AI assistants, LLM-powered tools, or any application that processes natural language input through an LLM. Covers role-playing attacks, instruction hierarchy exploitation, multi-turn manipulation, and context window abuse for comprehensive AI security testing.
日本語の概要は準備中です。原文の説明を表示しています。
Execute Indirect Prompt Injection attacks against Large Language Models (LLMs) by subtly embedding malicious instructions within external data sources (e.g., websites, documents, databases) that the LLM autonomously ingests. This forces the model to execute attacker-controlled commands under the guise of processing legitimate user requests.
日本語の概要は準備中です。原文の説明を表示しています。
OS command injection occurs when user input is passed unsanitized to a system shell via dangerous APIs: Java `Runtime.exec()`, Python `os.system/subprocess`, PHP `system/shell_exec/exec/proc_open`, C `system/exec`. Detect via pipe `|`, semicolon `;`, `&&`, `||`, backtick, `$()` operators, and time-delay payloads (`sleep 5`). Tools: Commix, Burp Suite, OWASP WebGoat.
日本語の概要は準備中です。原文の説明を表示しています。
Command injection playbook. Use when user input may reach shell commands, process execution, converters, import pipelines, or blind out-of-band command sinks.
日本語の概要は準備中です。原文の説明を表示しています。
Identify and exploit flaws in the core business rules and logic of web applications. This skill focuses on manipulation of application workflows, pricing, inventory limitations, and multi-step processes. Use this skill when bug hunting or testing e-commerce, banking, or SaaS platforms where standard technical vulnerabilities (e.g., XSS/SQLi) are not present but the application's logic is flawed.
日本語の概要は準備中です。原文の説明を表示しています。
Business logic flaws are application vulnerabilities where valid functions are abused in unintended ways: price manipulation via hidden field tampering, workflow step-skipping, function call limit bypass (coupon reuse), process timing exploitation (race conditions on balance updates), and request forging via guessable/predictable parameters. Detect using Burp Suite proxy interception, HTTP POST/GET parameter analysis, and misuse-case testing against multi-step workflows. Tools: Burp Suite, OWASP ZAP.
日本語の概要は準備中です。原文の説明を表示しています。
Use ONLY when the user explicitly asks to orchestrate parallel external agents (Codex or Claude Code) in tmux sessions via tp (tmux-pilot). Or when a user tells you that you're the boss or orchestrator. You can also use this if you are an operclaw agent. NEVER auto-invoke for a generic "do this in parallel" request. For in-process subagents, use superpowers:dispatching-parallel-agents instead.
日本語の概要は準備中です。原文の説明を表示しています。
Comprehensive ISA-101 design rules for Human Machine Interfaces in process automation, with detailed reference files covering color design, display hierarchy, navigation, alarms, human factors, performance, and lifecycle management. Use when designing, building, reviewing, or generating code for HMIs, control system displays, SCADA screens, or industrial control panels and comprehensive ISA-101 coverage is needed. Use when deep-diving into alarm design, color standards, navigation patterns, human factors, performance requirements, or HMI lifecycle management.
日本語の概要は準備中です。原文の説明を表示しています。
ISA-101 design rules for Human Machine Interfaces in process automation, covering display hierarchy, color standards, alarm integration, navigation, and situation awareness. Use when designing, building, reviewing, or generating code for HMIs, control system displays, SCADA screens, operator dashboards, or industrial control panels. Use when asked about ISA-101, alarm design, operator display hierarchy, or HMI color standards.
日本語の概要は準備中です。原文の説明を表示しています。
Use when integrating Celery with Django - task definition and calling, django-celery-beat scheduling, worker deployment, Flower monitoring, testing tasks, batch processing, or choosing between cron and beat
日本語の概要は準備中です。原文の説明を表示しています。
Full instrumentation from day one. PostHog consolidates product analytics + feature flags + error tracking (one platform, one bill). GA4 via GTM (14-step automation, custom dimensions over events, server-side tagging). Sentry (deep error tracking + performance). Stripe (webhook-first with idempotent processing). Listmonk on Coolify (newsletters via Amazon SES SMTP relay). PLG 7-layer framework. Programmatic SEO (5 page types). Incident auto-remediation via Sentry→Inngest pipeline. AI search (GEO) awareness. Local business conversions (phone_click, direction_click, form_submit, booking_click) with CRO patterns for both SaaS and local.
日本語の概要は準備中です。原文の説明を表示しています。
Supreme policy layer governing all agent behavior. Autonomy, one-line prompt interpretation, speed standards, emphasis signal processing, cross-skill coordination, done definitions, conflict resolution. Loaded every prompt.
日本語の概要は準備中です。原文の説明を表示しています。
Frappe Drive guidance for files, folders, sharing, permissions, storage, previews, document workflows, and file-linked business processes. Use when work touches Frappe Drive or file management in the Frappe ecosystem.
日本語の概要は準備中です。原文の説明を表示しています。
Frappe CRM guidance for leads, deals, contacts, organizations, pipelines, activities, assignment, dashboards, and sales workflows. Use when work touches Frappe CRM or CRM-style sales processes in the Frappe ecosystem.
日本語の概要は準備中です。原文の説明を表示しています。
Bench-aware Frappe operations guidance for app installs, branch switching, updates, migrations, site inspection, ports, and process state. Use when a task involves bench commands or local environment operations.
日本語の概要は準備中です。原文の説明を表示しています。
React Three Fiber (R3F) 3D rendering — Canvas, meshes, materials, lights, cameras, animations, events, physics, post-processing, performance
日本語の概要は準備中です。原文の説明を表示しています。
VisionCamera v4+ - photo/video capture, QR/barcode scanning, real-time frame processors, zoom/focus/exposure, HDR, location metadata, format selection
日本語の概要は準備中です。原文の説明を表示しています。
Background fetch, processing tasks, background location, headless JS, battery optimization - Expo and bare React Native
日本語の概要は準備中です。原文の説明を表示しています。
Electron process architecture, IPC patterns, preload security, native APIs, packaging and distribution
日本語の概要は準備中です。原文の説明を表示しています。
E2E testing with Playwright, main process unit testing, IPC testing, dialog/menu mocking, CI headless setup
日本語の概要は準備中です。原文の説明を表示しています。
Type-safe Electron IPC patterns with typed channels, electron-trpc, MessagePort, and utility process communication
日本語の概要は準備中です。原文の説明を表示しています。
Job queues, background processing, and task scheduling with BullMQ v5
日本語の概要は準備中です。原文の説明を表示しています。
Stripe payment processing — Checkout Sessions, Payment Intents, subscriptions, webhooks, Connect, customer management, error handling
日本語の概要は準備中です。原文の説明を表示しています。