'reverse' 검색 결과

Capture and analyze network traffic to understand custom protocols, including message boundaries and field meanings. Use the findings to document formats, investigate communication problems, and validate behavior through replay and tests with unusual inputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating network communication failures
• Understanding proprietary message formats
• Documenting protocol specifications

Build and troubleshoot C#/.NET MCP servers that expose tools and information to AI agents. Guidance targets the official 2.x SDK and covers transport setup, authentication, interactive features, basic clients, and migration issues caused by changed defaults.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a C#/.NET MCP server
• Add tools, prompts, and resources
• Diagnose STDIO and HTTP connection errors

Research competitors’ paid ads on Meta and Google, then examine their messaging, formats, and landing pages. Produce a strategy report showing paths from ads to signups, gaps in competitors’ approaches, and ideas for campaigns to test.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review the ad landscape before a campaign launch
• Compare competitors’ messages and ad formats
• Examine the path from an ad to a signup

Analyze malware communication with command servers to understand periodic check-ins, message formats, encoded data, and backup destinations. Produces a structured analysis report and network detection rules based on captured traffic and malware code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating malware communication in captured traffic
• Measuring periodic check-in intervals and timing variation
• Mapping command servers and backup destinations

Train smaller language models using knowledge distillation, where a larger model supplies examples or prediction targets. This skill covers training losses, generated training data, parameter choices, and output comparisons to support model compression and specialized student models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Training a smaller model from a larger teacher
• Fine-tuning with teacher-generated responses
• Distilling domain knowledge into a specialized model

Generate text and images through a reverse-engineered Gemini Web API, an interface reconstructed from the web service. Use reference images for descriptions or variations, and continue conversations across requests with saved sessions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generating images from written prompts
• Describing the contents of reference images
• Creating variations from an existing image

Deploy n8n on a Linux server using Docker Compose and Caddy for automatic HTTPS. Covers single-instance setups, workers for parallel execution, secret management, deployment checks, updates, backups, and restoration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Installing n8n on a VPS
• Running workflows in parallel with workers
• Publishing n8n with automatic HTTPS

Build coordinated animation sequences with GSAP timelines. Set when each movement starts, overlap effects, name key moments, combine smaller sequences, and control playback, including pause, reverse, restart, and jumps to a specific point.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Animating several elements in a planned order
• Overlapping effects at precise times
• Organizing animation sections with labels

Manually drive a vehicle in CARLA, set a target speed, operate lights and doors, and adjust mass or drag. You can also inspect the command topics used to control the main vehicle through ROS 2.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Manually test acceleration, steering, and braking
• Check vehicle lights and door operation
• Compare handling after changing mass or drag

Guide knowledge distillation, where a smaller language model learns from a larger teacher. Covers training from teacher responses or prediction scores, adjusting training settings, and comparing outputs to support model compression and specialized training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compressing a large language model into a smaller model
• Training a specialized model from teacher-generated examples
• Comparing distillation methods and training settings

Search shared game modding notes and turn session findings into reusable documentation. Record exact versions, engine behavior, verification limits, and fixes for common problems, then validate the note and prepare a public contribution for human approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Search existing notes before modding a game
• Find clues about an engine-specific problem
• Document verified findings after a modding session

Inspect game code, data files, live memory, and graphics captures to understand the internals needed for a mod. Choose tools for the game’s technology, document findings, and validate unknown file formats by decoding and re-encoding them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding boss behavior or damage calculations
• Investigating an undocumented game file format
• Locating player coordinates in live memory

Build chapter-based pages that move sideways as visitors scroll vertically. Deriving each scene from scroll position keeps reverse scrolling, jumps, and reloads consistent, with guidance for transitions, chapter links, keyboard controls, and reduced motion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a horizontal product tour
• Creating a chapter-based scrolling story
• Fixing scene mismatches after jumps or reloads

Deploy n8n on a Linux server using Docker Compose and Caddy for automatic HTTPS. Choose a single instance or queue workers, configure secrets and Python task runners, and follow procedures for updates, backups, and recovery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploy n8n on a personal VPS with HTTPS
• Set up queue workers for parallel workflow execution
• Update, back up, or restore an n8n instance

Turn reference images into prompts for AI image generation by describing composition, lighting, colors, and materials. Receive a main prompt and a negative prompt that specifies unwanted features, tailored to the image’s visual medium.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recreating a reference photo’s composition and lighting
• Turning an illustration’s visual style into a prompt
• Describing materials and backgrounds in product images

Turn a large codebase spanning multiple repositories or services into a structured knowledge base. It documents architecture, business rules, and dependencies, links conclusions to source lines, labels confidence in relationships, and supports incremental updates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Documenting architecture across multiple repositories
• Tracing service dependencies and business rules
• Updating a knowledge base after code changes

Guides agents to record confirmed final outcomes in history.md and correct entries when decisions change. This keeps handoff records clear enough for future agents to understand what actually happened without checking other files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording confirmed task outcomes
• Correcting a decision that was reversed
• Preparing history for an agent handoff

Investigate API requests that fail to replay because of client-generated signatures or anti-bot tokens. Start with captured traffic, identify the blocking inputs or signing function, and validate a reproducible request for further security testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate signature errors in replayed API requests
• Trace signing functions and their inputs
• Validate a reproduced signer against browser output

Map an existing app’s screens, user journeys, reusable interface parts, and likely data structure using public sources and your own account. Produce a research document and prioritized feature table to guide development of your own version.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Map an app’s screens and user journeys
• Define the scope of your own version
• Organize feature priorities before development

Investigate where or when a photo was taken using visible clues, metadata, reverse image search, maps, and image comparisons. Results include coordinates, an error radius, evidence images, and confidence levels that distinguish verified findings from uncertain candidates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating where a photo was taken
• Estimating capture time from sunlight and shadows
• Comparing location candidates against maps and street views

Provides reverse engineering techniques for CTF challenges. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, game clients, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Org-grade attack-surface mapping: given a company's legal identity, discover its ENTIRE owned internet footprint — corporate family -> owned domains -> owned netblocks/ASN -> live assets — with attribution discipline, not just DNS breadth. The org-first attribution pyramid (legal entity -> LEI/registration -> corporate family -> owned domains -> owned netblocks/ASN -> live assets). Corporate-identity resolution via the GLEIF LEI API (legal name -> LEI, exact-LEI direct-children expansion, downward-only depth-capped BFS, NEVER a name re-resolution), SEC-EDGAR full-text search + Exhibit-21 subsidiary entity names, OpenCorporates entity corroboration, Wikidata SPARQL corporate graph (P856/P355/P749/P1830). Domain attribution via reverse-WHOIS (WhoisXML preview-then-purchase quota guard, SecurityTrails associated-domains — both paid), crt.sh O= certificate-transparency organization pivot (keyless), infrastructure correlation (shared NS/MX/SaaS-TXT, netblock membership, reverse-DNS PTR), and the independent-evidence combiner (1-prod(1-w_i), rule of three, OwnerTier NONE/WEAK/MODERATE/STRONG/CONFIRMED) — discover-only `related:` candidates are NEVER auto-scanned. Netblock/ASN attribution via org-first RIR queries (ARIN Whois-RWS org-handle search, RIPE DB organisation + inverse-org search) that recover 'dark netblocks' with no DNS link to the seed, ASN discovery (RIPEstat + BGPView union), the HYPERSCALER-SCOPE GUARD (never attribute a whole AWS/GCP/Azure/Cloudflare announced range to a tenant — keep only the seed-containing block, tag shared_hosting_cdn), and org-identity-seeded internet-scan-index queries (Shodan/Censys/ZoomEye/FOFA/BinaryEdge org: filters + an always-on keyless crt.sh fallback). Promote-to-scan triage ranks forgotten discover-only netblocks by remote-access exposure (gateway-vendor/KEV/control-plane/datastore port scoring) into an operator queue. Attribution confidence rubric + anti-patterns (namesake grafting via GLEIF name re-resolution, single-signal ownership, hyperscaler over-attribution, privacy-WHOIS pivot poisoning, RIR org-name collisions). Passive/keyless-first OSINT only — every paid-key dependency is enrichment on top of a keyless core, never a hard requirement. Use when mapping an organization's full corporate-family internet footprint, resolving a legal entity to its LEI/subsidiaries, discovering domains/netblocks/ASNs an org owns beyond its one seed domain, auditing M&A/shadow-IT sprawl, or scoping an engagement that starts from a company NAME rather than a domain.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Custom VM and bytecode reverse engineering playbook. Use when CTF challenges or protected software implement custom virtual machines with proprietary bytecode, dispatcher loops, or maze-style challenges.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reverse shell techniques playbook. Use when establishing remote shells including language one-liners, encrypted shells (OpenSSL/socat/ncat), web shells, PTY upgrades, file transfer methods, PowerShell shells, and Windows payload generation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.