The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of playwright install chromium to download necessary browser binaries, which is a standard setup requirement for the Playwright library.
[EXTERNAL_DOWNLOADS]: The scrape_medium_to_html.py script fetches content from gist.githubusercontent.com to extract and include source code referenced in articles; this targets a well-known and trusted service.
[EXTERNAL_DOWNLOADS]: The script uses dynamic discovery to identify and fetch content from update URLs found within the text of scraped articles to ensure data completeness.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted web data. Ingestion points: Web content is retrieved via page.content() and external code via httpx.get() in scrape_medium_to_html.py. Boundary markers: None identified in the prompt templates. Capability inventory: The skill has the capability to write to the local file system and perform network requests. Sanitization: No specific content sanitization or instruction filtering is performed on the scraped data before it is presented to the agent.

web-scraping