sqldelight-patterns

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents patterns for ingesting and persisting data (such as user profiles and posts) into a local SQLite database.
  • Ingestion points: Data enters the system via UserRepository methods and is processed by queries in User.sq and Post.sq.
  • Boundary markers: While the documentation does not explicitly define LLM-specific boundary markers, the code implementation uses standard SQL parameterized queries (?).
  • Capability inventory: The skill enables persistent storage operations through platform-specific drivers (AndroidSqliteDriver and NativeSqliteDriver).
  • Sanitization: The implementation strictly follows best practices by using SQLDelight's type-safe generated code and prepared statements, which prevents traditional SQL injection attacks and provides a safe interface for data handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 08:11 PM
Security Audit — agent-trust-hub — sqldelight-patterns