skills/mineru98/k-skill/ktx-booking/Gen Agent Trust Hub

ktx-booking

Warn

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the korail2-ncard and pycryptodome Python packages from external registries. While pycryptodome is a standard library for cryptographic operations, korail2-ncard is a specialized package for Korail interactions that is not from a recognized trusted vendor.
  • [COMMAND_EXECUTION]: The skill relies on executing a local script scripts/ktx_booking.py to perform train searches, reservations, and cancellations. This script is the primary execution logic for the skill's capabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted user input (e.g., station names, travel dates, and train IDs) and processes this data through tools with command execution and file-system access capabilities.
  • Ingestion points: User-provided inputs for departure and arrival stations, dates, and times defined in SKILL.md.
  • Boundary markers: The skill instructions do not specify any delimiters or safety markers to isolate user-provided data from command parameters.
  • Capability inventory: The skill can execute shell commands via python3 and pip, and it manages a local credential file at ~/.config/k-skill/secrets.env.
  • Sanitization: No sanitization or validation logic is described to filter or escape user-provided arguments before they are passed to the helper script.
  • [DYNAMIC_EXECUTION]: The skill uses a python3 -c inline command to dynamically check for the presence of required libraries (korail2 and Crypto) before attempting to run the main script.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 9, 2026, 11:35 PM