'filesystem' 검색 결과

Anthropic 클라우드에서 에이전트를 실행하고 장시간 작업 요청, 진행 상황과 실행 기록 확인, 종료까지 관리합니다. 파일과 대화를 유지해 작업을 이어갈 수 있습니다.

• 장시간 작업을 클라우드에 위임
• 파일과 대화를 유지하며 작업 지속
• 세션 상태와 도구 사용 기록 확인

Review proposed file operations, commands, network access, secret handling, or destructive actions against explicit sandbox rules that define permitted activity. Receive a JSON verdict and the exact rule behind it without performing the proposed action.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing requested file operations before execution
• Checking commands or network access against sandbox rules
• Reviewing actions involving secrets or destructive changes

Answer questions about an agent's capabilities, memory, connected services, rules, and previous work by inspecting its actual files and workspace. Distinguish observed facts from inference and explain when evidence is missing, outdated, or incomplete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check what the agent can do for an active project
• Review what the agent remembers about the user
• Confirm connected services and operating rules

Automate browser tasks by exploring Chrome pages like folders. Agents can list page elements, read and search text, click controls, and fill forms through commands, with structured output and a persistent connection mode.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore page structure and read content
• Find text and click matching page elements
• Enter text into forms

Package a local MCP server, which connects an AI host to tools, as a .mcpb file. Include dependencies and runtime support, define installation settings, and validate, test, and sign the bundle for distribution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Package a local MCP server for distribution
• Offer installation without Node or Python setup
• Define folder selection and other installation settings

Review concrete code for exploitable security defects, including missing access checks, unsafe input handling, and exposed secrets. Report verified issues with file locations, reachable attack paths, severity, and suggested fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a code change for exploitable vulnerabilities
• Check authentication and access controls
• Trace unsafe input handling and secret exposure

Use the command line to discover and run tools on MCP servers, which connect agents to external systems. Inspect required inputs, pass JSON arguments, and retrieve results as JSON or raw text for scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Listing available MCP servers and tools
• Searching for tools by name
• Checking tool inputs before calling an external API

Inspect npm packages and dependency files for malicious installation scripts, credential theft, and self-spreading behavior. Use GuardDog scanning, source inspection, known-malicious version checks, and isolated execution to produce an evidence-based assessment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Vetting a new npm dependency before adoption
• Reviewing dependency files during code review
• Checking lockfiles against known-malicious versions

Investigate excessive privileges inside Kubernetes pods by reviewing security settings, runtime events, and audit logs. Use admission policies to restrict risky configurations and Falco monitoring to detect suspicious privilege changes and container activity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding pods running as root or in privileged mode
• Reviewing host filesystem access and dangerous Linux permissions
• Detecting privilege changes while containers are running

Detect unexpected changes in running containers by comparing them with their original images and monitoring execution and file activity. Use Falco or Microsoft Defender for Containers to investigate changes and guide isolation, replacement, and preventive configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding unexpected binaries executed inside running containers
• Investigating package installations and file changes at runtime
• Checking whether containers still match their approved images

Test iOS apps while they run using Objection and Frida, tools for inspecting and changing runtime behavior. Examine stored credentials, files, memory, and authentication calls, and evaluate client-side protections during authorized security assessments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check stored iOS app data for sensitive information
• Inspect HTTPS traffic during authorized testing
• Observe authentication behavior without source code

Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a GPU instance for LLM fine-tuning
• Keeping datasets and checkpoints between sessions
• Automating instance launch and termination through the API

Develop TypeScript services and workflows with Effect v4 by checking its source and existing project examples. Guides data schemas, typed errors, explicit dependencies, and tests that follow the project's established patterns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing services with Effect v4
• Defining data schemas and typed errors
• Organizing dependencies and HTTP handlers

Find and synthesize official Google developer documentation for platforms including Google Cloud, Gemini, Android, and Firebase. Retrieve command syntax, API details, permissions, and product comparisons through Developer Knowledge, then turn the findings into practical technical answers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking gcloud commands and flags
• Looking up API syntax and required permissions
• Comparing Google products and architectures

Run untrusted or AI-generated code in temporary microVMs, small virtual machines isolated from the host. Execute a snippet in one call, manage multi-step sessions, and read or edit files inside the sandbox.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run AI-generated code in an isolated environment
• Execute a snippet and collect its output
• Perform temporary builds or integration tests

Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing agents that edit their own conversation history
• Preserving exact values during long tasks
• Recovering from context overflow

Design persistent agent memory that retains knowledge across sessions and retrieves relevant facts when needed. Compare storage approaches, track people and changing information, and plan memory consolidation and evaluation based on the kinds of questions the agent must answer.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retain user preferences across conversations
• Track people and entities consistently across sessions
• Retrieve facts valid at a specific point in time

Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a GPU instance for LLM fine-tuning
• Keeping datasets and checkpoints between sessions
• Automating instance launch and termination through the API

Guide an agent through searching code, logs, and configuration files by content or filename. It explains which tools to choose, how to filter searches, and how to recognize incomplete results or searches requiring shell commands.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find TODO comments in Python files
• Search error logs with surrounding lines
• Locate configuration files by filename

Find workspaces on remote nodes, inspect their details, browse folders, and read or write files. Supports text files and binary content, such as images, through base64 encoding, a text representation of binary data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find workspaces on a specific remote node
• Browse folders and read project files
• Save output files to a remote workspace

Check whether a file creation or transformation task actually succeeded after an unclear execution error. Inspect output files and their contents to distinguish success, partial completion, and failure before deciding whether to retry.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking output files after an unknown error
• Validating spreadsheet or JSON contents
• Deciding whether to retry or fix incomplete output

Recover from file creation failures in automated tools by creating directories with shell commands and writing files individually. This workflow separates each step so project structures can be created and checked more easily.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recovering from unknown file creation errors
• Creating nested project directories
• Writing multiple files individually

Recover from failed file and directory operations by switching to run_shell, a shell command tool. Create nested folders, write files, and verify each result before continuing with tasks that depend on those files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retry file creation after an unknown error
• Create nested project folders explicitly
• Write files containing multiple lines

Review how evidence can be altered during authorized security exercises on Windows and Linux. Covers logs, timestamps, memory, disk records, and network traces, alongside the signs defenders use to detect manipulation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning authorized evidence manipulation tests
• Reviewing Windows and Linux forensic artifacts
• Checking detection coverage for altered evidence