effective-harnesses
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill automates project workflows by creating an initialization script (
init.sh) and executing it to start development environments. It also runs user-defined unit test commands (e.g.,npm test,pytest) to ensure features are correctly implemented before marking them as complete. - [EXTERNAL_DOWNLOADS]: The skill documentation and configuration reference official resources from
www.anthropic.comand GitHub for installation and guidance. These references target well-known and trusted sources. - [PROMPT_INJECTION]: The skill maintains its context through locally stored files such as
feature_list.jsonandclaude-progress.txt. While these act as ingestion points for the agent's state, they are used appropriately for progress tracking and task management in alignment with the skill's primary purpose.
Audit Metadata