anima-deploy-integration
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for a web service that ingests untrusted data (Figma file keys and node IDs) to generate code. This creates a surface for indirect prompt injection if malicious content is embedded within the design files processed by the SDK.
- Ingestion points: Data enters through
req.bodyin the Express and Vercel handler scripts (src/server.ts,api/generate.ts). - Boundary markers: The instructions explicitly mandate a "private or authenticated service boundary" and an "allowlisted design-file registry" in the Prerequisites to mitigate unauthorized access.
- Capability inventory: The skill utilizes
Bashtools for environment configuration and deployment (vercel,gcloud,docker) as specified in the frontmatter. - Sanitization: The documentation recommends a "validation pipeline" and "allowlisting" of design references to ensure only approved content is processed.
Audit Metadata