The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the requests library to facilitate API communication.
[COMMAND_EXECUTION]: Operates via a local Python script (search_twitter.py) that manages the scraping workflow.
[DATA_EXFILTRATION]: The script transmits the APIFY_API_TOKEN (or GOOSEWORKS_API_KEY) within URL query parameters to the vendor's proxy at app.gooseworks.ai. While this is targeting the author's own infrastructure, transmitting secrets in query strings is a suboptimal security practice as it can lead to credential exposure in server logs.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by processing arbitrary tweet content.
Ingestion points: scripts/search_twitter.py fetches data from the external Apify actor apidojo/tweet-scraper.
Boundary markers: Scraped data is returned as raw JSON without explicit delimiters or instructions to the agent to treat the content as potentially untrusted.
Capability inventory: The skill utilizes network access via requests and provides data to the agent that could influence subsequent tool calls.
Sanitization: No sanitization, filtering, or escaping of the tweet text is performed before it enters the agent's context.

twitter-scraper