seed
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute a local Node.js script (scripts/gen-seed.mjs). This script performs the core logic of parsing schemas and generating SQL statements based on user-provided arguments. - [DATA_EXPOSURE]: The skill is configured to read database schema definitions, ORM models, and migration files (such as
schema.prismaormodels.py). This access is localized to the project directory and is required for the tool's primary function. - [EXTERNAL_DOWNLOADS]: The skill does not contain instructions to download or execute code from external URLs or remote repositories.
- [PROMPT_INJECTION]: The instructions do not include any patterns typical of prompt injection, such as attempts to override agent behavior, disclose system prompts, or bypass content filters.
Audit Metadata