skills/ravnhq/ai-toolkit/tech-drizzle/Gen Agent Trust Hub

tech-drizzle

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): No patterns of prompt injection, role-play bypasses, or instructions to ignore safety filters were detected. The content is strictly focused on database development.
  • Data Exposure & Exfiltration (SAFE): The skill demonstrates positive security practices by explicitly recommending the exclusion of sensitive fields (e.g., passwordHash, resetToken) during database queries.
  • Evidence: rules/rqb-select-columns.md and rules/rqb-with-eager-loading.md provide code examples for column filtering.
  • Command Execution (SAFE): All included command-line examples are standard development operations (pnpm, git, cat) intended for local use. There are no patterns of piping remote content to a shell or suspicious subprocess spawning.
  • Indirect Prompt Injection (SAFE): While the skill processes user input for code generation, it is a static knowledge base with no ingestion of untrusted external data (APIs, web pages) and no high-risk capabilities like file writing or network requests.
  • Unverifiable Dependencies (SAFE): The documentation references well-known, industry-standard tools (drizzle-orm, drizzle-kit) and does not suggest the installation of suspicious or unversioned packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 08:40 PM