cva-variant-generator
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled data from Figma (component names, variant properties, and layer labels) which serves as an ingestion point for untrusted content. Maliciously crafted Figma files could attempt to influence the AI's generation process via these strings.\n
- Ingestion points: Figma design-file context including frames, components, instances, layers, and properties as identified in SKILL.md.\n
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within ingested data are provided.\n
- Capability inventory: The skill is restricted to generating text-based code blocks (CVA configurations) and lacks capabilities for network access or unauthorized file system operations.\n
- Sanitization: There are no requirements in the skill's workflow to sanitize or validate the content extracted from the Figma environment.
Audit Metadata