Kotlin Multiplatform

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate technical documentation and templates for Kotlin Multiplatform development.\n- [PROMPT_INJECTION]: No instructional overrides or safety bypass attempts were detected.\n- [DATA_EXFILTRATION]: No sensitive data exposure or unauthorized network exfiltration patterns were found. Network calls use generic placeholders for demonstration.\n- [REMOTE_CODE_EXECUTION]: The skill does not contain patterns for executing arbitrary remote scripts or untrusted code.\n- [EXTERNAL_DOWNLOADS]: Dependencies listed are industry-standard libraries (Ktor, SQLDelight, Coroutines) referenced via Gradle version catalogs.\n- [OBFUSCATION]: No Base64, zero-width characters, or other encoding techniques intended to hide malicious intent were present.\n- [INDIRECT_PROMPT_INJECTION]: The skill describes data ingestion from external APIs and local databases, which is expected for its purpose. \n
  • Ingestion points: ApiClient fetches from remote URLs; UserDataSource reads from local SQLite in SKILL.md.\n
  • Boundary markers: Not explicitly defined in these generic templates.\n
  • Capability inventory: Network operations via Ktor; local database writes/reads via SQLDelight drivers.\n
  • Sanitization: Standard JSON parsing using kotlinx-serialization with ignoreUnknownKeys enabled.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 03:36 AM
Security Audit — agent-trust-hub — Kotlin Multiplatform