harvard-artifacts-data-engineering-analytics
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the application source code from a GitHub repository (Manali0711/Harvard-Artifacts-Collection-Data-Engineering-Analytics-App) and installs standard libraries such as pandas and requests via pip.
- [PROMPT_INJECTION]: The skill involves processing external data from the Harvard Art Museums API. Ingestion points: Data enters the pipeline via the fetch_artifacts function targeting api.harvardartmuseums.org. Boundary markers: No explicit delimiter instructions are provided for the AI agent handling the metadata. Capability inventory: The skill utilizes network requests (requests library) and database interactions (mysql-connector-python). Sanitization: The implementation uses parameterized SQL queries (cursor.executemany) to safely handle artifact metadata during the database load phase.
- [CREDENTIALS_UNSAFE]: Correctly implements secure credential management by instructing the use of environment variables and .env files for storing the Harvard API key and database connection details.
- [SAFE]: No malicious code, obfuscation, or persistence mechanisms were detected. The skill follows established patterns for data engineering tasks.
Audit Metadata