tdd-refactor-guard
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes project source code and tests, creating a surface for indirect prompt injection.
- Ingestion points: Files and classes identified for refactoring are read via the
ReadandGreptools (SKILL.md). - Boundary markers: Absent; the skill does not explicitly use delimiters or instructions to ignore commands embedded in the code it analyzes.
- Capability inventory: The skill has access to
Write,Edit, andBashtools. - Sanitization: None; the skill does not perform sanitization on the content of the files it processes.
- [COMMAND_EXECUTION]: The skill uses
Bashto executexcodebuildfor running unit tests. This is a standard and expected operation for a tool designed to verify code integrity in a development environment.
Audit Metadata