The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (tweets and replies) fetched from X (Twitter).
Ingestion points: Data is ingested via fetch_user_tweets, fetch_tweet_replies, and fetch_niche_top methods as described in the Steps section of SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the ingested tweet content.
Capability inventory: The skill utilizes lib.ApifyClient() for network-based data retrieval and suggests integration with other writing tools like x-post-writer.
Sanitization: There are no explicit mentions of sanitizing or escaping the fetched social media content before analysis.
[SAFE]: The skill references Apify, a well-known web scraping and automation service, for its data retrieval layer. The use of an API token (APIFY_TOKEN) for authentication is a standard and safe practice for this type of integration.

x-audience-insights