itinerary

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): The instructions provide functional guidelines for itinerary creation and do not attempt to bypass agent safety filters or extract system prompts.
  • Data Exposure & Exfiltration (SAFE): No sensitive file paths or credential extraction patterns were found. The skill references standard public domains for travel and government information.
  • Indirect Prompt Injection (SAFE): The skill ingests external data from travel websites and has a write capability (calendar updates). This potential attack surface is mitigated by the requirement for 'explicit confirmation' from the user before any calendar events are created.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): No package managers (npm, pip) or remote script execution (curl|bash) patterns are present in the files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:07 PM