materials-project

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Uses curl to perform GET requests against the official Materials Project API endpoint (api.materialsproject.org). These operations are restricted to querying materials properties such as band gaps and crystal structures.
  • [COMMAND_EXECUTION]: Employs python3 -c to execute a short, inline script for parsing JSON results from the API. The script is static, provided within the skill's instructions, and processes data received via standard input (stdin).
  • [CREDENTIALS_UNSAFE]: Instructions correctly advise the user to store their API key in an environment variable (MP_API_KEY) rather than hardcoding it, which aligns with security best practices for credential management.
  • [EXTERNAL_DOWNLOADS]: Fetches materials science data from https://api.materialsproject.org/v3, which is a well-known and legitimate scientific resource managed by the Lawrence Berkeley National Laboratory. No executable code or unverified packages are downloaded.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:30 PM
Security Audit — agent-trust-hub — materials-project