building-with-ai-agents
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown files providing educational frameworks and mental models for AI-driven development. No executable scripts or system modifications are present.
- [SAFE]: All included prompt templates (such as /review, /exploration, and the AI Agent Builder Meta-Prompt) are designed for user-initiated task delegation and architectural planning. They do not contain instructions to bypass safety filters or override agent constraints.
- [SAFE]: The skill references established industry tools and platforms (e.g., Cursor, Claude Code, Linear, GitHub, Zapier) in an educational context. There are no attempts to download or execute code from untrusted remote sources.
- [SAFE]: Includes a 'Security Risk Evaluation for AI Agents' artifact that promotes security best practices, such as using least-privilege permissions and consulting internal security officers (CISOs).
Audit Metadata