tech-drizzle
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of documentation and code examples that follow industry best practices for TypeScript and database management. The commands and patterns described (e.g.,
drizzle-kit push,db.transaction) are standard for the Drizzle ORM ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing user-supplied database schemas and query requirements. This represents a typical surface for indirect prompt injection in coding assistants, but it is limited to the skill's primary purpose of database design and does not involve automatic ingestion of external, untrusted content from the web.
- Ingestion points: Processes user-provided schema files and query descriptions within the local development environment.
- Boundary markers: The skill does not define specific delimiters for separating instruction from data, relying on standard model context management.
- Capability inventory: The skill utilizes file system tools (Read, Write, Edit, Glob) and shell access (Bash) for developer workflows.
- Sanitization: Relies on the agent's internal safety guardrails and the type-safety provided by the Drizzle ORM framework itself.
Audit Metadata