harvard-art-museum-etl-analytics

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the user or agent to clone and install code from a third-party GitHub repository (https://github.com/Manali0711/Harvard-Artifacts-Collection-Data-Engineering-Analytics-App.git) that does not belong to a verified or trusted organization.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8):
  • Ingestion points: Data enters the context via the fetch_artifacts function from the Harvard Art Museums API in SKILL.md.
  • Boundary markers: None identified to delimit external API content from agent instructions.
  • Capability inventory: Includes database write operations (load_to_database) and interactive visualization displays (show_analytics_page).
  • Sanitization: Uses parameterized SQL queries for database safety but lacks sanitization or filtering of external text content before it is processed or displayed in the dashboard.
  • [COMMAND_EXECUTION]: Instructions involve executing shell commands (git clone, pip install, streamlit run) which lead to the installation and execution of code downloaded from an untrusted source.
  • [SAFE]: Credentials and API keys are managed using environment variables (os.getenv) and .env files, adhering to recommended secret management practices.
  • [SAFE]: Network activity is restricted to the legitimate API endpoint for the Harvard Art Museums (api.harvardartmuseums.org).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 09:21 AM
Security Audit — agent-trust-hub — harvard-art-museum-etl-analytics