The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches data from the official Hacker News API (hacker-news.firebaseio.com). This is a well-known service and the downloads are limited to public JSON data.
[COMMAND_EXECUTION]: Uses curl and jq to retrieve and process API responses. The usage follows standard patterns for data retrieval and does not involve executing remote scripts or commands.
[DATA_EXFILTRATION]: Network activity is strictly confined to the Hacker News API for fetching public information. No sensitive local files or credentials are accessed or transmitted.
[PROMPT_INJECTION]: As the skill processes untrusted external data (story titles, comments, and user bios) from Hacker News, there is a theoretical surface for indirect prompt injection.
Ingestion points: API responses in SKILL.md (e.g., story text, user bios).
Boundary markers: None present.
Capability inventory: curl, jq in SKILL.md.
Sanitization: None present.

hackernews