anima-reference-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a reference architecture for automating design-to-code workflows using the Anima SDK. It does not contain malicious code or active instructions.\n- [SAFE]: The design incorporates security best practices, including deployment secret management, webhook signature verification, and least-privilege access.\n- [INDIRECT_PROMPT_INJECTION]: The architecture defines a surface for processing external design data (Figma webhooks), which the skill mitigates through allowlisting and human verification.\n
- Ingestion points: External Figma Design components and Webhook events via API described in
SKILL.md.\n - Boundary markers: Mandatory allowlisting for Figma file and node IDs; manual owner review before merge.\n
- Capability inventory: Uses
WriteandEdittools to generate pull requests and build artifacts.\n - Sanitization: Includes secret scanning, normalization, and visual regression checks.
Audit Metadata