flyai

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation advises users to install the @fly-ai/flyai-cli Node package. This tool is required to interface with the travel search services provided by the vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes natural language input for various travel search functions, which is a common pattern for AI agents.
  • Ingestion points: The query and keyword parameters across all search subcommands in the references directory.
  • Boundary markers: No specific delimiters are mandated in the documentation for separating user input from system instructions.
  • Capability inventory: The skill leverages the flyai CLI to execute network operations for real-time travel data retrieval.
  • Sanitization: The reference files do not explicitly document input sanitization, which is assumed to be handled within the CLI binary or the service API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:38 AM
Security Audit — agent-trust-hub — flyai