The Agent Skills Directory

[SAFE]: The skill uses curl to interact with hacker-news.firebaseio.com, which is a well-known service used by the official Hacker News API. These requests are limited to fetching publicly available JSON data.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from external sources (story titles, comments, and user bio text) which could potentially contain prompt injection instructions.
Ingestion points: Hacker News API responses for items and user profiles, specifically the text, title, and about fields.
Boundary markers: None are provided to separate fetched content from the agent's instructions.
Capability inventory: The skill utilizes curl for network access and jq for data processing.
Sanitization: No sanitization or validation of the fetched text is performed before it is processed by the agent.

hackernews