kotlin-kmp-refactor-safety
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a set of best-practice guidelines for code refactoring, focusing on safety, reviewability, and regression testing. It does not contain any executable code or instructions that bypass safety protocols.
- [DATA_EXPOSURE]: The skill includes explicit instructions for maintaining security during observability implementation, specifically warning against logging secrets, tokens, or personal data.
- [COMMAND_EXECUTION]: The skill is configured with a restricted set of read-only tools (
Read,Grep,Glob), which limits the agent's ability to perform unauthorized modifications or system-level changes. - [INDIRECT_PROMPT_INJECTION]: While the skill guides the agent on how to process existing code, it does not ingest untrusted data from external sources and maintains a low risk profile regarding prompt injection.
Audit Metadata