The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches RSS feed data from several external domains listed in the references/feeds.opml file. These domains include established technology blogs and well-known personal websites.
[PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which creates a surface for indirect prompt injection.
Ingestion points: Content is fetched from external RSS feed URLs in scripts/aggregate.py using the feedparser library.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the output provided to the agent.
Capability inventory: The skill is limited to reading feeds and printing summaries; it does not contain capabilities for system modification or sensitive file access.
Sanitization: The clean_summary function in scripts/aggregate.py strips HTML tags and normalizes text, providing basic protection against code injection but not against natural language instructions.

rss-aggregator