The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and run the @nomadamas/k-skill package from the NPM registry to retrieve the primary instructions and helper files.
[REMOTE_CODE_EXECUTION]: The skill uses npx to execute remote code from the author's official NPM package for various operations, including instruction fetching (instruct), file listing (files), and executing the main Python script (exec).
[COMMAND_EXECUTION]: The skill prompts the agent to execute shell commands using npx and Python to interact with the location data script located at scripts/seoul_density.py.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes real-time data from an external API proxy (k-skill-proxy.nomadamas.org), which could theoretically contain malicious instructions if the upstream source or proxy is compromised.
Ingestion points: API responses fetched using urllib.request in scripts/seoul_density.py.
Boundary markers: Absent; the script outputs the parsed data directly to the agent's context without delimiters.
Capability inventory: The script performs network GET requests and outputs formatted strings to the terminal.
Sanitization: The script performs JSON parsing and extracts specific fields (e.g., AREA_CONGEST_LVL, AREA_PPLTN_MIN) rather than passing the raw response.

seoul-density