kotlin-multiplatform-expert
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute a local Python validation script (
scripts/validate_skill_map.py) to ensure the skill index remains synchronized with the repository. It also prescribes the use ofgrepcommands to inspect local source code for specific implementation patterns, such as Ktor clients or RPC services, to facilitate accurate architectural routing. These operations are performed on local files for development purposes and involve no external or high-risk command execution.\n- [INDIRECT_PROMPT_INJECTION]: As an orchestrator, the skill is designed to process untrusted local data, including project READMEs and source code, to generate recommendations. The 'Freshness Rule' explicitly instructs the agent to treat the local repository files as the source of truth, establishing a context boundary for the analysis of project-specific content.
Audit Metadata