'code-execution' 검색 결과

Guide shell, Python, and Node.js execution on the computer running a connected A0 CLI. It explains session reuse, interactive input, output retrieval, and recovery steps when execution permissions, timeouts, or disconnections interrupt the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run shell commands on the connected A0 CLI host
• Execute Python or Node.js on the host
• Retrieve output or answer an interactive program

Inspect and control the connected local computer through A0 CLI or a Launcher host gateway. The skill guides screenshots, native app input, window targeting, and checking results, with background actions where the connected system supports them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect the screen of a connected local computer
• Click controls and enter text in native apps
• Target a particular app window for desktop actions

Create and edit Excel workbooks by running a complete Python script through the shell. Covers multiple sheets, data entry, formatting, formulas, and saving files when other file-reading or code-execution tools fail.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create an Excel report with multiple sheets
• Apply data and formatting in one script
• Update cells in an existing XLSX file

Run Python code through a saved script and shell when repeated sandbox failures point to environment problems. Captures execution output and checks exit codes and expected files to verify whether the task completed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing work after repeated sandbox execution failures
• Running Python scripts saved in the workspace
• Investigating failures through shell error output

Recover from failed code execution by simplifying code, switching to shell commands, or handing complex tasks to shell_agent. Explicit working directories and output checks help keep generated files in the expected location.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recovering from sandbox execution failures
• Keeping generated files in the intended folder
• Checking output files after code execution

Continue Python tasks after repeated sandbox failures by saving code as a script and running it through the shell, a command interface. The workflow covers execution checks, result retrieval, and optional cleanup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing data processing after repeated sandbox errors
• Saving execution results to files for later retrieval
• Checking script errors and exit codes

Test whether an AI agent executes commands hidden in user input, evaluates untrusted code, or runs scripts from unverified sources. Record confirmed weaknesses with the test conversation, potential impact, and suggested safeguards.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking command injection in shell-enabled agents
• Testing whether user input is executed as code
• Reviewing how agents load remote scripts

Probe AI agents through dialogue to check for unexpected command execution, file access outside intended paths, and prompted network requests. It selects tests based on available tools and records confirmed behavior with conversation evidence and mitigation suggestions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking agents that can run commands or code
• Testing file access beyond intended directories
• Checking whether prompts trigger URL requests

Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or secure multi-tenant execution. Also suited for AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs, dev environments running user-supplied code), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, or isolated security scanners. Also applicable when the workload needs long-lived sessions, a real port-listening server (gRPC, WebSocket, custom TCP protocols), state preserved across periods of inactivity (suspend/resume), container-level access (FUSE, eBPF, custom syscalls), or session-affine routing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build, run, debug, and operate applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments that run inside a container with up to 8-hour lifetimes. Triggers on: Lambda MicroVMs, Firecracker isolation, snapshot-resumable compute, suspend/resume, sandboxed or untrusted code execution, AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, isolated security scanners, long-lived sessions, or port-listening servers (gRPC, WebSocket, custom TCP). For standard event-driven Lambda functions, use the aws-lambda skill instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does arithmetic/parsing/data transforms, when prose reasoning hallucinates a computation (under-coding), or when a sandbox round- trip is wasted on a judgment task (over-coding). Search keywords: code interpreter, agent does math wrong, calculator hallucination, when to run code vs reason, program of thought, PoT, tool vs reasoning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

E2B is a cloud platform that gives AI agents secure, isolated sandboxes — ephemeral Linux VMs with a filesystem, package managers, and internet access — to run AI-generated code safely. Use when a user wants an agent to execute Python or JavaScript, install packages, read/write files, or run a long process without risking the host machine, or wants to wire code execution into a LangChain, CrewAI, or custom agent loop.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when an editor MCP server (unity, godot, unreal, blender) or the browser MCP shows up in your tool list - what each one can observe or change, how to check it is attached to YOUR task workspace, why the repo's tests still decide, the Blender code-execution caution, and the headless fallback when none is connected.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create, inspect, and edit Word documents (`.docx`) with local code-execution tools. Use for document drafting, structured edits, tables, comments, and layout-sensitive Word deliverables.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Read, create, edit, and verify PDFs with local code-execution tools and rendered-page inspection. Use whenever PDF layout, forms, extraction, merging, or final visual quality matters.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Senior {{engine_name}}/{{engine_code_language}} developer that performs direct, ad-hoc code tasks without a formal plan — and the code-execution engine other unikit skills and agents delegate to. Use it whenever the user asks to do something in code right now, e.g. "add this method to this class", "refactor this function", "write a script that does X", "change this code", "optimize this class". Phrases like "without a plan", "no plan", "just do it", or "directly" are strong signals to use this skill rather than planning. Covers writing, refactoring, optimizing, and discussing {{engine_code_language}} code and patterns (DI, ECS, MVC, state machines, event systems). For a larger multi-step feature, plan it with /unikit-plan and build it with /unikit-implement — this skill is for direct, unplanned code work.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

MS17-010 (EternalBlue) is a critical vulnerability in Microsoft's SMBv1 implementation that allows remote code execution. Originally discovered by the NSA and leaked by the Shadow Brokers in 2017, it

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.