epd-research

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses WebSearch and WebFetch to find public environmental product data, which is its primary function. All target domains (e.g., buildingtransparency.org, ul.com, nsf.org) are official industry registries.
  • [SAFE]: The use of Google Sheets tools (mcp__google__sheets_values_update) is documented and intended for saving research results to a user-provided spreadsheet. No hardcoded credentials or sensitive file access were detected.
  • [SAFE]: The skill instructions do not attempt to override AI safety filters or exfiltrate sensitive system information. It provides clear boundary guidance on when to ask the user for sheet IDs or API keys.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 11:58 AM
Security Audit — agent-trust-hub — epd-research