trip-plan
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes the
WebFetchtool to ingest content from travel blogs and theWebSearchtool for travel research. This represents an ingestion point for untrusted external data that could potentially contain malicious instructions. - Ingestion points: WebFetch is used to gather information from external travel blogs in Phase 1B.
- Boundary markers: The instructions do not explicitly specify the use of delimiters or 'ignore' warnings for the fetched content.
- Capability inventory: The skill has
WriteandEditpermissions, primarily used to generate and save a Markdown itinerary file (tripbot-{destination}-{YYYY-MM-DD}.md). - Sanitization: No explicit sanitization or validation of the fetched web content is mentioned before it is processed or included in the final export.
- [COMMAND_EXECUTION]: The skill uses the
Writetool to export the final itinerary to a file. The filename is dynamically generated based on the destination and date, but the scope is limited to the current directory and the content is restricted to the trip data collected during the conversation.
Audit Metadata