agent-tool-builder
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily educational, offering templates and architectural patterns for tool development without including executable malicious code.
- [SAFE]: The instructions explicitly promote security best practices, including mandatory input validation and a specific requirement for parameterized SQL queries to prevent injection attacks.
- [SAFE]: Dependency references are limited to standard, well-known SDKs for AI development (Anthropic SDK, MCP SDK, Zod) used for illustrative purposes.
Audit Metadata