developer-database-specialist
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill explicitly instructs the agent to never expose administrative credentials, connection strings, or service keys in any outputs.
- [SAFE]: The instructions mandate the use of parameterized queries and prepared statements to prevent SQL injection vulnerabilities.
- [SAFE]: The skill enforces secure access models, including Row Level Security (RLS) for SQL databases and user validation in Firebase Security Rules.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted data from product requirement documents and scrum backlogs. However, this is inherent to its primary purpose and is mitigated by the skill's strict output requirements.
- Ingestion points: Product Requirement Documents (PRD) and Scrum Backlog items mentioned in SKILL.md.
- Boundary markers: None explicitly defined to separate untrusted instructions.
- Capability inventory: Generation of SQL DDL, Firebase Security Rules, and database migration scripts.
- Sanitization: Instructions require the agent to verify that generated code utilizes parameterization and authentication checks.
Audit Metadata