harvard-art-museum-etl-pipeline
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a source code repository from a personal GitHub account (github.com/Manali0711/Harvard-Artifacts-Collection-Data-Engineering-Analytics-App.git).
- [COMMAND_EXECUTION]: Provides instructions to install Python packages via a requirements file and execute a Streamlit web application, which runs code from the downloaded repository.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a pipeline that ingests data from an external source (Harvard Art Museums API).
- Ingestion points: Data records fetched from
api.harvardartmuseums.orginSKILL.md. - Boundary markers: Data is processed as structured JSON; however, there are no specific boundary delimiters or instructions for the agent to disregard potential instructions embedded within artifact metadata.
- Capability inventory: The skill has the capability to write to a SQL database and render interactive charts in a web browser.
- Sanitization: The provided code implementation uses parameterized SQL queries (%s placeholders) to mitigate database injection risks.
Audit Metadata