The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted data from external sources.
Ingestion points: Scrapes guest bios and event descriptions from Luma and Apify actor results in apify_client.py and scrape_event.py.
Boundary markers: Absent; there are no delimiters or instructions to treat the scraped data as untrusted content.
Capability inventory: The skill writes extracted data to local CSV and JSON files and prints data to the console.
Sanitization: No sanitization or escaping is performed on the ingested text before it is returned to the agent.
[EXTERNAL_DOWNLOADS]: The skill requires the standard requests library for its network operations.
[DATA_EXFILTRATION]: The skill makes legitimate network requests to apify.com and lu.ma to fetch event and profile data, which is necessary for its core functionality.

luma-event-attendees