meta-travel-planner
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code or suspicious behavior patterns were identified. The skill correctly implements a multi-step workflow for travel planning.
- [PROMPT_INJECTION]: The skill ingests user input via the
user_messagevariable and processes it through multiple LLM steps. It uses thexml_escapefilter during the initial extraction phase, which helps sanitize the input before it is used in subsequent prompts. This reduces the risk of indirect prompt injection affecting the tool queries (weather/search) or the final itinerary generation.
Audit Metadata