The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches data from the official Hacker News (Firebase) and Algolia search APIs. These are well-known services used appropriately for the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-generated content from Hacker News which could theoretically contain malicious instructions.
Ingestion points: The scripts/hn.py script retrieves stories, comments, and user profiles from external API endpoints.
Boundary markers: Absent. The content is retrieved and displayed without specific delimiters or ignore-instruction warnings.
Capability inventory: The skill's capabilities are restricted to network read operations (GET requests) using httpx; it lacks file system write access or shell command execution capabilities.
Sanitization: The skill employs an html_to_text function that uses regular expressions to strip HTML tags and unescape characters from the input data before it is displayed.

ez-hn