newsletter-voice
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely on local project files (
voice.md,about-me.md) and user-provided chat inputs. - [SAFE]: There are no instances of command execution, network requests, or external script loading.
- [SAFE]: The
AskUserQuestiontool is used for benign configuration purposes (selecting an archetype). - [SAFE]: File creation (
newsletter-voice.md) is restricted to the project root and based on clear, safe templates defined in the reference files. - [SAFE]: The instructions do not contain prompt injection patterns; they enforce logic to ensure prerequisites are met before proceeding.
Audit Metadata