The Agent Skills Directory

[Prompt Injection] (SAFE): The instructional content is strictly limited to business logic for stock screening. No patterns indicative of prompt injection, such as 'ignore instructions' or safety bypass attempts, were detected.\n- [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive file paths or credentials. Network usage is consistent with fetching financial data for the specified tickers.\n- [Unverifiable Dependencies & Remote Code Execution] (SAFE): There are no occurrences of remote script downloads (curl/wget) or execution of scripts from external, untrusted sources.\n- [Command Execution] (SAFE): The skill invokes a local script scripts/screen_stock.py with ticker parameters. This is a standard functional pattern for AI agent skills and does not involve elevated privileges or suspicious command execution.

sharia-screening