harvard-artifacts-etl-streamlit
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches museum artifact data and associated media information from the Harvard Art Museums public API (api.harvardartmuseums.org).
- [EXTERNAL_DOWNLOADS]: Instructs the user to clone the project's source code from a public GitHub repository (github.com/Manali0711/Harvard-Artifacts-Collection-Data-Engineering-Analytics-App.git).
- [COMMAND_EXECUTION]: Provides standard instructions for installing Python dependencies and running the Streamlit dashboard locally via the command line.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes data from an external API.
- Ingestion points: Artifact metadata and descriptions are retrieved from the Harvard Art Museums API within the Python extraction scripts.
- Boundary markers: No explicit delimiters or instructions are provided to the model to ignore potential instructions embedded in the API data.
- Capability inventory: The skill includes database write operations (SQL INSERTs) and UI rendering (Streamlit/Plotly).
- Sanitization: The provided code correctly uses parameterized SQL queries (e.g., using %s placeholders) to sanitize external data before database insertion.
Audit Metadata