principle-subtract-before-you-add
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based architectural principles and configuration settings. It does not contain any code, external dependencies, or instructions that interact with the system or network. No patterns of prompt injection, data exfiltration, or obfuscation were detected. The YAML frontmatter specifically disables model invocation, which significantly limits the execution context.
Audit Metadata