The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill requires the use of npx to fetch its primary instructions and execute updates. This involves downloading and running code from the @nomadamas/k-skill package at runtime, which bypasses static review of the full instructional content.
[COMMAND_EXECUTION]: The workflow relies on executing shell commands via npx to run a local Python script (scripts/komsa_ferry_info.py), creating a bridge between the agent environment and external script execution.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to k-skill-proxy.nomadamas.org and mtisopenapi.komsa.or.kr to retrieve ferry schedules and vessel data.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external APIs (schedules, ports, and vessel specs) which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Data is ingested in scripts/komsa_ferry_info.py via urllib.request.urlopen calls to the proxy.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the script's output formatting.
Capability inventory: The skill possesses network access and the ability to execute Python scripts.
Sanitization: While the script uses standard JSON decoding, it does not apply specific sanitization or filtering to the text content within the API responses before outputting it to the agent.

komsa-ferry-info