tauri-app-sql
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-defined SQL queries and database configurations, which represents an indirect prompt injection surface.
- Ingestion points: SKILL.md specifies triggers for user mentions of SQL, migrations, and database engines.
- Boundary markers: The instructions lack explicit delimiters to isolate untrusted user input within the generated integration plans.
- Capability inventory: templates/capabilities.json defines broad permissions for SQL operations using wildcards (e.g., INSERT INTO *) on a specific SQLite database.
- Sanitization: Although the skill mentions validation in its steps, it lacks concrete implementation patterns for sanitizing external content before interpolation.
- [SAFE]: External references point to official tauri.app domains, which are well-known and verified services.
- [SAFE]: The skill includes documentation and configuration templates without any executable scripts or binary files.
Audit Metadata