dbml-database-docs
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted metadata from various database sources which may contain embedded instructions.\n
- Ingestion points: Reads data from SQL migration files, ORM model definitions, Doctrine entity mappings, and database dumps as sources for generating DBML documentation.\n
- Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within the ingested schema content.\n
- Capability inventory: The skill can write to repository files like
db/schema.dbmlandspecs/features/, and it can execute the local./scripts/check-schema-drift.shscript.\n - Sanitization: Absent; no validation or filtering is performed on strings or comments extracted from the database sources.\n- [COMMAND_EXECUTION]: The skill executes a predefined local script.\n
- The instructions command the agent to run
./scripts/check-schema-drift.shto validate documentation and detect schema drift.
Audit Metadata