v1.0.0

Universal Data Model for the next generation of AI-driven smart spaces

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:48 AM.

Analysis

This skill appears to generate a local smart-space JSON template and does not show evidence of credential use, networking, hardware control, or data exfiltration.

GuidanceThis skill looks safe for its stated purpose: it generates a local JSON data-model template. Before using the generated schema with real smart-home or spatial-control agents, review what data you put into it and make sure connected agents treat the template as structured data rather than as unrestricted instructions.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityInfoConfidenceHighStatusNote

skill.py

PRIMITIVE_DIR = os.path.join(os.getcwd(), "s2_primitive_data") ... with open(TEMPLATE_FILE, 'w', encoding='utf-8') as f:

The script creates a directory and writes a local JSON file. This is scoped and matches the stated template-generation purpose, but users should know it will modify the current working directory.

User impactRunning the skill will create or overwrite a local template file named primitive_6_elements_template.json under s2_primitive_data.

RecommendationRun it from a directory where creating or replacing that template file is acceptable.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceMediumStatusNote

SKILL.md

Supply this JSON schema to your OpenClaw agents as the baseline context for spatial awareness and control.

The generated schema is meant to be reused as agent context and contains many natural-language fields. This is purpose-aligned, but future filled-in values should be treated as data, not automatically trusted instructions.

User impactIf users later populate the template with real smart-space data, agents may rely on that context when reasoning about the environment.

RecommendationKeep populated spatial data from trusted sources and avoid allowing arbitrary text in these natural-language fields to act as instructions to the agent.