travel-planner

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are purely text-based and focus on generating travel itineraries. There are no calls to external tools, network requests, or filesystem operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided travel details (destination, dates, budget). While this is an ingestion point for external data, the skill lacks any executable capabilities or sensitive data access that could be exploited via indirect injection. The instructions provide clear boundaries for the expected output format.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 04:18 AM
Security Audit — agent-trust-hub — travel-planner