railway-timetable

Warn

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and backend functionality depend on the installation of the @nomadamas/k-skill package from the npm registry.
  • [REMOTE_CODE_EXECUTION]: The skill uses npx -y @nomadamas/k-skill@0 as the primary method to fetch instructions and execute Python backend scripts, which downloads and runs external code at runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its ingestion of untrusted external data.
  • Ingestion points: scripts/ktx_backend.py fetches JSON metadata from www.korail.com and downloads XLSX timetable files.
  • Boundary markers: Absent; there are no delimiters or instructions provided to the agent to disregard content within the ingested timetable data.
  • Capability inventory: Network read access via urllib.request and the ability to parse Excel workbooks using openpyxl.
  • Sanitization: Station names and timetable 'notes' from the external XLSX files are included in the JSON output without sanitization or escaping.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 1, 2026, 02:41 PM