Powerdrill Data Analysis
PassAudited by ClawScan on May 1, 2026.
Overview
This appears to be a coherent Powerdrill data-analysis helper, with expected but important use of API credentials, local-file uploads, persistent analysis resources, and dataset deletion features.
Install this only if you are comfortable giving it a Powerdrill project API key and uploading selected files to Powerdrill for analysis. Confirm before deleting datasets or sessions, use least-privileged credentials where possible, and clean up temporary resources after use.
Findings (4)
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.
The skill can perform Powerdrill API actions using the user's project credentials.
The skill requires a Powerdrill user ID and project API key to act on the user's Powerdrill account. This is expected for the integration, but users should recognize the delegated account authority.
export POWERDRILL_USER_ID="your_user_id" export POWERDRILL_PROJECT_API_KEY="your_project_api_key"
Use a project-scoped key with only the access needed, store it securely in environment variables, and rotate it if exposed.
A mistaken dataset ID or unconfirmed cleanup could delete Powerdrill data and its data sources.
The client includes irreversible dataset deletion. The artifact discloses this and instructs confirmation, so it is purpose-aligned but high-impact enough for user attention.
delete_dataset(dataset_id) -> dict` Permanently delete a dataset and all its data sources. **Irreversible** - always confirm with the user first.
Confirm dataset and session IDs with the user before deletion or cleanup, especially for existing or shared datasets.
Uploaded files, questions, and analysis context may remain available in Powerdrill until the user deletes the dataset or session.
Powerdrill sessions preserve analysis context across jobs, and uploaded datasets are managed in the user's Powerdrill account. This persistence is part of the purpose but affects sensitive data handling.
Session - A conversation context that maintains history across multiple analysis jobs
Avoid uploading data that should not leave the local environment, and clean up temporary datasets and sessions when finished.
The user may need to install a Python dependency before using the client.
The skill relies on the external Python requests package, while the install specification lists no install step. This is a common, purpose-aligned dependency, but it should be installed from a trusted package source.
pip install requests
Install dependencies from a trusted Python package index or a pinned, reviewed environment.