The Agent Skills Directory

[PROMPT_INJECTION]: No instructions attempting to bypass safety guidelines, override core agent behavior, or extract system prompts were detected.- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path access, or unauthorized network transmission patterns were found. The skill does not instruct the agent to exfiltrate user data.- [REMOTE_CODE_EXECUTION]: No patterns of downloading and executing scripts from remote or untrusted sources (e.g., curl|bash) are present.- [COMMAND_EXECUTION]: The skill does not contain any dangerous system commands, shell scripts, or privilege escalation attempts.- [EXTERNAL_DOWNLOADS]: Includes links to well-known and reputable educational resources (storytellingwithdata.com, duarte.com) and standard book links, which are treated as safe references.- [DYNAMIC_EXECUTION]: The skill includes a benign Python code snippet for data visualization using standard libraries (matplotlib, pandas). This is provided as a template for user reference and does not represent unsafe dynamic execution.

data-storytelling