design-spec

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly auto-routes and extracts context from Figma URLs ("If Figma URL provided → auto-routes to /figma-design to extract context" in SKILL.md), so it ingests third-party/user-generated content and then uses that content to drive subsequent actions and decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly auto-routes and extracts content from user-provided Figma URLs (e.g., https://www.figma.com/file or https://figma.com/design) at runtime and injects that fetched content into the agent’s context to drive the spec generation, so the external Figma URL can directly control prompts.