A diagnostic and telemetry tool for identifying if an AI agent is running in a sandbox, container, or on bare metal.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-setup-survey
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-setup-survey using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Agent Setup Survey?
Agent Setup Survey is a specialized diagnostic utility designed to help developers and researchers analyze the runtime environment of AI agents. By executing local detection scripts, it identifies whether an agent is running within a container, a virtual machine, or directly on bare metal hardware. This skill is a valuable addition to the collection of Openclaw Skills for those contributing to open-source research on agentic workflows and infrastructure security.
The tool prioritizes user privacy by displaying all collected signals for manual review before any transmission occurs. It enables the community to gather anonymized telemetry about how different LLM providers and local agent frameworks interact with system-level resources, helping to map the landscape of modern AI deployments.
Agent Setup Survey Use Cases
- Contributing to open research on AI agent deployment patterns and infrastructure.
- Verifying the isolation levels and sandbox constraints of an AI agent environment.
- Auditing the system-level visibility an AI agent has within its current execution context.
- Benchmarking the compatibility of various Openclaw Skills across different OS architectures.
How Agent Setup Survey Works
- Run the local detection script to scan for virtualization and containerization signals.
- Generate a temporary JSON report containing system architecture, OS details, and hypervisor flags.
- Present the raw JSON output to the user to ensure transparency and consent.
- Optionally collect metadata regarding other installed agent skills to enrich the research dataset.
- Transmit the anonymized payload to the research backend via a secure POST request.
Agent Setup Survey Setup
This skill requires Python 3 and temporary network access for submission. Ensure your environment allows executing scripts and creating temporary files.
# Create a directory for local results
mkdir -p outbox
# Execute the detection survey
RESULT_FILE="$(mktemp outbox/agent-setup-survey-result.XXXXXX.json)"
python3 scripts/environment-survey.py > "$RESULT_FILE"
Agent Setup Survey Data Schema & Taxonomy
The skill organizes environment data into a structured JSON format to ensure compatibility with research dashboards. Below is the primary data taxonomy:
| Field | Description |
|---|---|
os |
Operating system family (linux, windows, macos) |
arch |
CPU architecture (e.g., x86_64, arm64) |
container |
Object containing boolean is_container and runtime type |
vm |
Object containing boolean is_vm and hypervisor type |
signals |
Boolean flags for specific environment indicators like has_dockerenv or cgroup_hints |
skill_disclosure |
Optional metadata including the number and names of active Openclaw Skills |
Agent Setup Survey Advanced Features
- Automated detection of five distinct system signals to identify sandboxed environments.
- Local outbox caching for manual upload if network access is restricted or submission fails.
- Dynamic User-Agent identification to track which LLM models and versions are used for submission.
- Granular privacy controls allowing users to select exactly which Openclaw Skills are disclosed in the report.
SKILL.md
Loading
Related Openclaw Skills
ePragma Redmine Issue
A powerful interface for managing Redmine issues, projects, and time tracking entries through a secure REST API integration.
Fluid Memory
A bio-inspired memory system for AI agents that mimics human cognition by prioritizing frequently accessed information and naturally decaying irrelevant data.
Send USD
A specialized skill designed to facilitate secure and automated USD currency transfers between autonomous AI agents.
ASUSTOR Pro Adaptive Suite
A hardware-aware, hybrid SMB and SSH suite designed to scrape ASUSTOR NAS metadata while maintaining strict system safety and resource efficiency.
ABL.ONE Canonical Language
A high-density, binary communication protocol that enables agents to interact via strict token frames instead of natural language.
AgentWard Sanitize
A security-first PII redaction tool that locally detects and masks sensitive information with zero external dependencies.
Featured*
