skills/delorenj/skills/android-kotlin/Gen Agent Trust Hub

android-kotlin

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's Gradle configuration references standard Android and Kotlin dependencies from well-known and trusted providers including Google (AndroidX, Dagger/Hilt, Room) and JetBrains (Kotlin, Coroutines). These are standard industry dependencies for the specified task.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates for interacting with external data sources such as network APIs and local databases, which represents a standard data ingestion surface.
  • Ingestion points: Untrusted data enters the agent context through network responses (via Retrofit/Ktor) and local database queries (via Room) as described in the repository and DAO templates in SKILL.md.
  • Boundary markers: The skill follows Clean Architecture patterns, using repositories and domain models to structure data flow, though it does not explicitly define AI-specific prompt delimiters for the data being processed.
  • Capability inventory: The skill outlines capabilities for network communication and local file system writes (database persistence) required for Android application functionality.
  • Sanitization: The skill relies on standard Kotlin type safety and data modeling to validate structure, which is consistent with the intended purpose of providing development templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:55 AM
Security Audit — agent-trust-hub — android-kotlin