drizzle
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from
https://orm.drizzle.team/llms.txtand various paths underhttps://orm.drizzle.team/docs/. These are the official documentation sources for the Drizzle ORM project. - [INDIRECT_PROMPT_INJECTION]: The skill processes external content fetched from the web (Drizzle ORM documentation) via a research sub-agent.
- Ingestion points: Documentation pages under
orm.drizzle.teamdescribed inSKILL.md. - Boundary markers: The skill provides a structured prompt template for the research sub-agent to maintain task focus.
- Capability inventory: The sub-agent uses the
WebFetchtool to retrieve documentation; theTasktool is used to manage the research process. - Sanitization: Not explicitly mentioned, but content is retrieved from a well-known official source for informational purposes.
Audit Metadata