kotlin-kmp-refactor-safety
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing guidelines for change discipline and architectural cleanup without including executable scripts or remote resource fetches.
- [SAFE]: The 'Observability' section explicitly mandates security best practices by instructing the agent never to log secrets, tokens, passwords, or personal data.
- [SAFE]: The instructions emphasize scope control and PR hygiene, which are defensive practices that reduce the risk of accidental logic changes or malicious code insertion during large refactors.
- [SAFE]: No indicators of prompt injection, obfuscation, data exfiltration, or persistence mechanisms were found in the provided markdown content.
Audit Metadata