harvard-art-museums-data-engineering-app
Warn
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to clone a repository from an unverified GitHub account ('Manali0711'). Downloading and running code from unknown sources introduces a significant supply chain risk.
- [INDIRECT_PROMPT_INJECTION]: The skill implements an ETL pipeline that ingests data from the Harvard Art Museums API and renders it in a Streamlit dashboard.
- Ingestion points: Data is fetched from
api.harvardartmuseums.orgin thefetch_artifactsfunction. - Boundary markers: No delimiters or instructions are used to separate external data from agent commands.
- Capability inventory: The skill uses
requestsfor network access andmysql-connector-pythonfor database operations. - Sanitization: There is no evidence of sanitization or filtering for potentially malicious strings within the API responses before they are displayed in the dashboard.
- [COMMAND_EXECUTION]: The documentation includes shell commands for installation and execution (
git clone,pip install,streamlit run) that result in the execution of third-party code and installation of remote packages.
Audit Metadata