srt-booking
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the 'SRTrain' Python package from the public registry (PyPI) to handle SRT API interactions.
- [COMMAND_EXECUTION]: The skill executes Python logic via shell here-docs ('python3
- <<'PY'') to perform search, reservation, and cancellation operations.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because user-provided inputs like station names and dates are intended to be interpolated into the Python scripts executed by the agent.
- Ingestion points: User-supplied '출발역' (Departure), '도착역' (Arrival), and '날짜' (Date) fields are processed as untrusted data.
- Boundary markers: Absent.
- Capability inventory: The skill can execute Python code in a subprocess and access environment variables ('KSKILL_SRT_ID', 'KSKILL_SRT_PASSWORD').
- Sanitization: None; the workflow assumes direct interpolation of user inputs into the Python script strings.
Audit Metadata