anima

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

• Third-party content exposure detected (high risk: 0.90). The skill's core flows explicitly ingest arbitrary public website URLs (playground-create type="l2c" with a url parameter, e.g., "Clone the Linear homepage") and external Figma files (codegen-figma_to_code from Figma URLs), so untrusted third-party content is read and directly drives generation/publishing behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires an Anima MCP server at https://public-api.animaapp.com/v1/mcp for runtime calls (playground-create, codegen-figma_to_code, playground-publish, project-download_from_playground), which executes remote operations and generates code/playgrounds that directly drive agent behavior, so this external endpoint is a required runtime dependency that executes remote code.