The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data fetched from Facebook, including page descriptions and user comments, which introduces a potential surface for indirect prompt injection if malicious instructions are embedded in that content.
Ingestion points: Data retrieved from page_url and post_url via Apify methods described in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present for the external data processing.
Capability inventory: Uses lib.ApifyClient() to fetch data; no file-write or shell execution capabilities are present.
Sanitization: No explicit sanitization or filtering of the fetched content is documented.
[EXTERNAL_DOWNLOADS]: The skill utilizes the Apify platform and specifically references the apify/facebook-pages-scraper and danek/facebook-comments-ppr actors to retrieve live social media data.

fb-audience-insights