The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'SRTrain' Python package from PyPI. This is a vendor resource provided by the skill author to facilitate interaction with the SRT booking system.
[COMMAND_EXECUTION]: The workflow involves executing local Python scripts using shell commands to process travel data and perform bookings. These scripts are generated based on user-provided inputs such as departure and arrival stations.
[DATA_EXFILTRATION]: The skill handles SRT login credentials using a secure resolution order. It encourages the use of environment variables or a local configuration file with restricted filesystem permissions (0600), minimizing the risk of credential exposure to unauthorized local users.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data from the SRT train search API.
Ingestion points: Data enters the system context through the 'srt.search_train' and 'srt.get_reservations' function outputs in the SKILL.md workflow.
Boundary markers: The instructions do not define explicit delimiters to separate the library's output from the agent's logic.
Capability inventory: The skill has the capability to execute Python scripts and perform authenticated network requests to the SRT service.
Sanitization: No explicit sanitization or validation of the data returned by the SRT library is performed before it is processed by the AI agent.

srt-booking