kmp-repositories

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate software architecture templates for Kotlin Multiplatform development. Analysis of the code samples and instructions revealed no evidence of prompt injection, data exfiltration, or obfuscated malicious payloads.- [INDIRECT_PROMPT_INJECTION]: The skill defines a data ingestion architecture (Remote and Local data sources) in SKILL.md. While this establishes a potential surface for indirect prompt injection if the resulting application processes untrusted user data, the skill itself is a structural template and does not contain exploitable injection logic.
  • Ingestion points: UserRemoteDataSource (API responses) and UserLocalDataSource (Database).
  • Boundary markers: Not applicable for code templates.
  • Capability inventory: Network requests via API and local storage via SQLDelight queries.
  • Sanitization: Standard implementation is not specified in the architectural template.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 08:11 PM
Security Audit — agent-trust-hub — kmp-repositories