pie-design-system

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 5 "Cross-Reference Figma" workflow requires the agent to accept a user-provided Figma URL and call get_design_context / get_metadata to fetch and map Figma file/node content (user-generated, public third-party content) which the agent must read and use to choose components, creating a clear path for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs runtime fetching of Figma design data (e.g. https://figma.com/design//?node-id=) via get_design_context and uses the returned design to map components, meaning externally-fetched content would directly control the agent's decisions.