design-to-code

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to run a command passing a placeholder Figma API token (figd_...) directly as a command-line argument, which encourages insecure handling of secrets.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow fetches Figma designs via URL where any outsider can author text layers or design content that gets processed into prompts and ingested by the agent.