ai-prompting
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE: The skill consists entirely of instructional documentation and utility scripts that perform local string processing. There are no network requests, file system modifications, or hardcoded credentials.
- INDIRECT_PROMPT_INJECTION (INFO): Scripts like
optimize-prompt.pyandprompt-optimizer.pyprocess user-provided strings for analysis. However, since these scripts only perform basic pattern matching and output text to the console without any execution capability (noeval,exec, or subprocess calls on user data), the risk is negligible. - EXTERNAL_DOWNLOADS (SAFE): All references in the documentation point to trusted documentation sites for OpenAI and Anthropic.
Audit Metadata