dbml-database-docs
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a project-local shell script
./scripts/check-schema-drift.shto validate that the DBML documentation is synchronized with the actual database schema. This is a standard practice for maintaining documentation integrity. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository, including SQL migration files, ORM entities, and database comments, which constitutes a potential ingestion surface for indirect instructions.
- Ingestion points: Reads files such as
db/schema.dbml, migration files, and ORM model definitions (SKILL.md). - Boundary markers: The instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within schema source files.
- Capability inventory: The agent is authorized to write to
db/schema.dbmland execute local scripts (SKILL.md). - Sanitization: There is no explicit instruction for sanitizing or escaping metadata or comments extracted from the database sources.
Audit Metadata