figma-to-generateblocks
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including Figma URLs, screenshots, and user-provided design descriptions, to generate code. This creates a surface for indirect prompt injection where a malicious design could attempt to influence the agent's behavior. However, the skill's primary function is static code generation, and the output is restricted to WordPress block format.
- Ingestion points: Processes Figma URLs, images, and text descriptions provided by the user in the prompt.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the design content.
- Capability inventory: The skill uses file-writing capabilities to output converted designs as
.htmlfiles. - Sanitization: No specific sanitization or validation logic is defined for the input data before processing.
Audit Metadata