kotlin-kmp-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a rigorous code review process for Kotlin Multiplatform projects, focusing on best practices, separation of concerns, and maintainability. It does not request any dangerous permissions or tool access.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided code and pull requests, which constitutes an ingestion surface for indirect prompt injection. However, the risk is negligible as the skill lacks executable capabilities and provides strict internal guidelines for the agent to follow when evaluating external content.
- Ingestion points: Review of Kotlin Multiplatform code, refactors, PRs, and bug fixes in SKILL.md.
- Boundary markers: None explicitly defined.
- Capability inventory: None (The skill only generates textual review reports).
- Sanitization: Not applicable as there are no tool calls or code execution paths.
Audit Metadata