harvard-artifacts-data-engineering-app

Warn

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to clone a repository from https://github.com/Manali0711/Harvard-Artifacts-Collection-Data-Engineering-Analytics-App.git, which is an unverified personal account not associated with a known trusted organization.
  • [COMMAND_EXECUTION]: The setup instructions involve executing multiple shell commands, including git clone, pip install -r requirements.txt, and streamlit run app.py.
  • [REMOTE_CODE_EXECUTION]: By directing the agent to download and install a repository and its dependencies from an unverified source, the skill introduces the risk of executing untrusted or malicious code.
  • [DYNAMIC_EXECUTION]: The build_custom_query function in the skill's documentation demonstrates unsafe SQL query construction using string interpolation (e.g., f\" AND culture = '{filters['culture']}'\"). This pattern is a security vulnerability (SQL Injection) that could allow unauthorized database commands if user-supplied input is not properly sanitized or parameterized.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 1, 2026, 01:35 PM
Security Audit — agent-trust-hub — harvard-artifacts-data-engineering-app