The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to override agent behavior or bypass safety filters. The language used is purely instructional and focused on database best practices.- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration operations were detected.- [Remote Code Execution] (SAFE): No patterns involving the download or execution of remote scripts or unverified dependencies were identified.- [Indirect Prompt Injection] (SAFE): The skill processes user requests for database modeling. Evidence: 1. Ingestion points: User input (e.g., 'add category function'); 2. Boundary markers: Absent; 3. Capability inventory: Generates TypeORM code; 4. Sanitization: Instruction 4 explicitly forbids string concatenation in SQL queries to prevent injection.- [Command Execution] (SAFE): No shell commands or subprocess spawning logic found within the instructions.

database-expert