api-database-drizzle
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions facilitate reading data from an external PostgreSQL database through the Drizzle ORM (see examples/queries.md).
- Ingestion points: Data retrieved from database tables such as jobs and companies in examples/queries.md.
- Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters or to treat fetched database content as potentially containing malicious instructions.
- Capability inventory: The skill environment enables writing code files and executing shell commands for database management (e.g., bun run drizzle-kit, bun add drizzle-seed).
- Sanitization: While the code examples correctly utilize Drizzle's safe SQL templating to prevent SQL injection, they do not include instructions for sanitizing or escaping the resulting data before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the drizzle-seed package using the bun package manager in examples/seeding.md. This is an official component of the Drizzle ORM ecosystem used for generating development data.
Audit Metadata