travel-agent-skill

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from web search results to generate travel itineraries, which is a standard surface for indirect prompt injection.
  • Ingestion points: WebSearch tool results (SKILL.md).
  • Boundary markers: No specific delimiters are used to wrap external content.
  • Capability inventory: Web search and HTML file generation.
  • Sanitization: No explicit content sanitization is mentioned.
  • [DYNAMIC_EXECUTION]: The skill generates a self-contained HTML guide file for the user to open in a browser.
  • Evidence: The 'Export Guide' feature generates a '自包含HTML攻略文件' (self-contained HTML guide file) as described in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 10:39 PM
Security Audit — agent-trust-hub — travel-agent-skill