principle-subtract-before-you-add
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill content is entirely composed of conceptual design and refactoring principles. There are no executable scripts, shell commands, or automation instructions that could perform actions on a host system.
- [SAFE]: No data ingestion surfaces were identified. The skill does not process external input or interact with external APIs, eliminating the risk of indirect prompt injection.
- [SAFE]: The frontmatter configuration includes
disable-model-invocation: true, which restricts the skill's ability to call other AI models, providing an additional layer of execution safety.
Audit Metadata