recipe-forward-labeled-emails

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gws command-line tool to perform operations on Gmail. Specifically, it lists messages with the label 'needs-review', retrieves the content of those messages, and sends a new email containing that content.
  • [DATA_EXFILTRATION]: The skill is designed to forward email content to manager@company.com. While this involves sending data to an external address, it aligns perfectly with the skill's stated purpose of email forwarding and does not show signs of malicious exfiltration.
  • [SAFE]: The skill follows a standard workflow for task automation. It does not use obfuscation, attempt privilege escalation, or include unauthorized remote code execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — recipe-forward-labeled-emails