skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/equipment-fleet-manager/Gen Agent Trust Hub
equipment-fleet-manager
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements logic for managing construction equipment fleet data, including utilization reports and maintenance scheduling within the
EquipmentFleetManagerclass. - [SAFE]: Dependencies are limited to
pandas, which is a standard and well-known library for data analysis and manipulation. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided data formats like Excel, CSV, and JSON, which is a common pattern for data management skills.
- Ingestion points:
instructions.mdspecifies that the agent should accept project data, file paths, or parameters from the user. - Boundary markers: No explicit prompt boundary markers are defined in the instructions to separate user data from agent instructions.
- Capability inventory: The skill has filesystem write access as declared in
claw.json, utilized via theexport_fleetmethod inSKILL.mdusingpandas.to_excel. - Sanitization: While the instructions specify that the agent should "Validate inputs before processing", the provided Python code serves as a data structure and logic layer without specific sanitization routines for the input data.
Audit Metadata