powerdrill-data-analysis

This skill should be used when the user wants to analyze, explore, visualize, or query data using Powerdrill. Covers listing, creating, and deleting datasets; uploading local files as data sources; creating analysis sessions; running natural-language data analysis queries; and retrieving charts, tables, and insights. Triggers on requests like "analyze my data", "query my dataset", "upload this file for analysis", "list my datasets", "create a dataset", "visualize sales trends", "continue my previous analysis", "delete this dataset", or any data exploration task mentioning Powerdrill.

Before installing: 1) Note the registry metadata omits required env vars — you must set POWERDRILL_USER_ID and POWERDRILL_PROJECT_API_KEY for the skill to work. 2) The skill can read and upload arbitrary local files to https://ai.data.cloud/api; avoid pointing it at sensitive system files or secrets and only upload data you control. 3) Verify the API endpoint and documentation (confirm ai.data.cloud/api is the correct Powerdrill endpoint for your account) and limit the API key scope/permissions where possible. 4) Because the source/homepage is unknown, prefer installing only if you trust the publisher; consider testing in an isolated environment with a throwaway API key and dataset, and do not enable broad autonomous access for agents that have filesystem access unless you explicitly allow the specific file operations you want.

Type: OpenClaw Skill Name: powerdrill-data-analysis-skill Version: 1.0.0 The skill provides a Python client for the Powerdrill Data Analysis API, enabling data upload, analysis, and management. All network communication is directed to the legitimate `https://ai.data.cloud/api` endpoint. The script reads API credentials from environment variables, which is standard for API clients. File system access is limited to reading a specified `file_path` for upload, a core function of the skill. There is no evidence of intentional harmful behavior such as unauthorized data exfiltration, malicious execution, persistence, or prompt injection attempts against the agent in the documentation or code.