The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @nomadamas/k-skill@0.2.4 package from the npm registry. This external tool is used to display updated instructions and run the bundled Python script.
[DATA_EXFILTRATION]: User-provided text or file content is sent to nara-speller.co.kr via HTTP POST requests for processing. The skill includes clear documentation and warnings regarding this external data transmission and its privacy implications.
[INDIRECT_PROMPT_INJECTION]: The skill processes responses from an external web service, which could potentially serve as a vector for indirect prompt injection if the service returns malicious content.
Ingestion points: External text is retrieved from the nara-speller.co.kr service in scripts/korean_spell_check.py via the fetch_spell_check_html function.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the processing flow.
Capability inventory: The skill possesses capabilities for reading local files (Path.read_text) and performing network operations (urllib.request).
Sanitization: The script performs HTML unescaping and tag stripping on returned content, but it does not implement specific filtering or validation to prevent prompt injection attacks.

korean-spell-check