The Agent Skills Directory

[SAFE]: The skill demonstrates secure development practices by utilizing environment variables for API keys (TWITTER_API_KEY and OPENROUTER_API_KEY) and routing network traffic through the platform's recommended proxy settings. All identified network operations target well-known services for the purpose of social media analysis and AI processing.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Twitter API and interpolates it into prompts for an LLM. While this is necessary for the skill's analytical functions, it creates a surface where malicious tweet content could attempt to influence the agent's output.
Ingestion points: Tweet text is fetched via scripts/api_client.py using the get_twitter_user_timeline and search_twitter_tweets methods.
Boundary markers: The skill employs JSON-formatted prompts and triple-quote delimiters in scripts/content_generator.py and scripts/twitter_analyzer.py to distinguish untrusted content from system instructions.
Capability inventory: The skill possesses network capabilities to communicate with Twitter and OpenRouter APIs and provides formatted text/JSON output to the user.
Sanitization: Content is processed through weighted engagement algorithms and statistical analysis prior to LLM interpolation to identify relevant patterns.

creator-insights