railway-timetable

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches railway timetable indices (JSON) and schedule files (XLSX) from the official Korail website (www.korail.com).
  • [REMOTE_CODE_EXECUTION]: Instructs the agent to download and execute code from the NPM registry using 'npx -y @nomadamas/k-skill@0'. This package belongs to the skill's author and is used to provide updated instructions and execute the backend scripts.
  • [COMMAND_EXECUTION]: Utilizes shell commands via npx to interact with the vendor-provided CLI tool and execute Python scripts using 'uv run'.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill downloads and parses XLSX files from the Korail website board in 'scripts/ktx_backend.py'.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are present when processing the external data.
  • Capability inventory: The skill has the capability to perform network requests and execute subprocess commands via npx.
  • Sanitization: Implements station name normalization and regex-based validation for train numbers, departure/arrival times, and dates in 'scripts/ktx_timetable.py' and 'scripts/ktx_backend.py'.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:49 AM
Security Audit — agent-trust-hub — railway-timetable