figma

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated Figma content from third-party endpoints (e.g., curl to https://api.figma.com/v1/files/$FILE_KEY and https://api.figma.com/v1/files/$FILE_KEY/comments) and then uses those nodes/data as input for code-generation, exposing the agent to untrusted third-party content.