The Agent Skills Directory

[SAFE]: No malicious behavior or high-risk security patterns were identified. Technical details of the analysis follow:\n- [DATA_EXFILTRATION]: The script scripts/search_twitter.py performs network operations to api.apify.com and api.gooseworks.ai. It handles the Apify API token (retrieved from environment variables or command-line arguments) as a query parameter in these requests. This communication is directed to well-known service endpoints and does not involve unauthorized data access or sensitive file exfiltration.\n- [COMMAND_EXECUTION]: The skill provides scripts/search_twitter.py, a Python utility script intended for searching Twitter posts via the Apify platform. This script is a functional component of the skill designed to be executed within the agent's runtime environment.\n- [PROMPT_INJECTION]: The skill ingests content from an untrusted external source (Twitter/X). This represents a surface for indirect prompt injection where malicious instructions within a tweet could potentially influence the agent's behavior. This risk is inherent to the primary function of social media scraping and monitoring tools.

twitter-mention-tracker